### Introduction to LangChain with Harrison Chase, creator of LangChain
- [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
- [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@FullStackDeepLearning)
@ -13,7 +14,7 @@
## Videos (sorted by views)
- [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
- [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson)
- [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson)
- [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
@ -37,7 +38,7 @@
- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
- [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
- [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld)
- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld)
- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nick_daigs)
- [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
- [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
@ -108,7 +109,7 @@
- ⛓ [How to Run `LLaMA` Locally on CPU or GPU | Python & Langchain & CTransformers Guide](https://youtu.be/SvjWDX2NqiM?si=DxFml8XeGhiLTzLV) by [Code With Prince](https://www.youtube.com/@CodeWithPrince)
- ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
](https://www.youtube.com/@AkamaiDeveloper)
](https://www.youtube.com/@AkamaiDeveloper)
- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIDataScienceOnAWS)
- ⛓ [`LLAMA2 70b-chat` Multiple Documents Chatbot with Langchain & Streamlit |All OPEN SOURCE|Replicate API](https://youtu.be/vhghB81vViM?si=dszzJnArMeac7lyc) by [DataInsightEdge](https://www.youtube.com/@DataInsightEdge01)
- ⛓ [Chatting with 44K Fashion Products: LangChain Opportunities and Pitfalls](https://youtu.be/Zudgske0F_s?si=8HSshHoEhh0PemJA) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
@ -123,8 +124,8 @@
- ⛓ [Build Chat PDF app in Python with LangChain, OpenAI, Streamlit | Full project | Learn Coding](https://www.youtube.com/watch?v=WYzFzZg4YZI) by [Jutsupoint](https://www.youtube.com/@JutsuPoint)
- ⛓ [Build Eminem Bot App with LangChain, Streamlit, OpenAI | Full Python Project | Tutorial | AI ChatBot](https://www.youtube.com/watch?v=a2shHB4MRZ4) by [Jutsupoint](https://www.youtube.com/@JutsuPoint)
### [Prompt Engineering and LangChain](https://www.youtube.com/watch?v=muXbPpG_ys4&list=PLEJK-H61Xlwzm5FYLDdKt_6yibO33zoMW) by [Venelin Valkov](https://www.youtube.com/@venelin_valkov)
- [Getting Started with LangChain: Load Custom Data, Run OpenAI Models, Embeddings and `ChatGPT`](https://www.youtube.com/watch?v=muXbPpG_ys4)
- [Loaders, Indexes & Vectorstores in LangChain: Question Answering on `PDF` files with `ChatGPT`](https://www.youtube.com/watch?v=FQnvfR8Dmr0)
To contribute to this project, please follow the ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
@ -13,6 +14,7 @@ Pull requests cannot land without passing the formatting, linting, and testing c
[Formatting and Linting](#formatting-and-linting) for how to run these checks locally.
It's essential that we maintain great documentation and testing. If you:
- Fix a bug
- Add a relevant unit or integration test when possible. These live in `tests/unit_tests` and `tests/integration_tests`.
- Make an improvement
@ -34,7 +36,7 @@ For a [development container](https://containers.dev/), see the [.devcontainer f
This project utilizes [Poetry](https://python-poetry.org/) v1.7.1+ as a dependency manager.
❗Note: *Before installing Poetry*, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
❗Note: _Before installing Poetry_, if you use `Conda`, create and activate a new Conda env (e.g. `conda create -n langchain python=3.9`)
Install Poetry: **[documentation on how to install it](https://python-poetry.org/docs/#installation)**.
@ -44,6 +46,7 @@ tell Poetry to use the virtualenv python environment (`poetry config virtualenvs
### Different packages
This repository contains multiple packages:
- `langchain-core`: Base interfaces for key abstractions as well as logic for combining them in chains (LangChain Expression Language).
- `langchain-community`: Third-party integrations of various components.
- `langchain`: Chains, agents, and retrieval logic that makes up the cognitive architecture of your applications.
@ -219,16 +222,20 @@ any side effects (no warnings, no errors, no exceptions).
To introduce the dependency to the pyproject.toml file correctly, please do the following:
1. Add the dependency to the main group as an optional dependency
```bash
poetry add --optional [package_name]
```
```bash
poetry add --optional [package_name]
```
2. Open pyproject.toml and add the dependency to the `extended_testing` extra
3. Relock the poetry file to update the extra.
```bash
poetry lock --no-update
```
```bash
poetry lock --no-update
```
4. Add a unit test that the very least attempts to import the new code. Ideally, the unit
test makes use of lightweight fixtures to test the logic of the code.
test makes use of lightweight fixtures to test the logic of the code.
5. Please use the `@pytest.mark.requires(package_name)` decorator for any tests that require the dependency.
To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](./code).
@ -18,7 +19,7 @@ In the following sections, we'll walk through how to contribute to each of these
The `langchain-community` package is in `libs/community` and contains most integrations.
It can be installed with `pip install langchain-community`, and exported members can be imported with code like
It can be installed with `pip install langchain-community`, and exported members can be imported with code like
```python
from langchain_community.chat_models import ChatParrotLink
@ -26,7 +27,7 @@ from langchain_community.llms import ParrotLinkLLM
from langchain_community.vectorstores import ParrotLinkVectorStore
```
The `community` package relies on manually-installed dependent packages, so you will see errors
The `community` package relies on manually-installed dependent packages, so you will see errors
if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
Let's say we wanted to implement a chat model for Parrot Link AI. We would create a new file in `libs/community/langchain_community/chat_models/parrot_link.py` with the following code:
@ -61,11 +62,11 @@ And add documentation to:
Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
Partner package in the `LangChain` repo is placed in `libs/partners/{partner}`
Partner package in the `LangChain` repo is placed in `libs/partners/{partner}`
and the package source code is in `libs/partners/{partner}/langchain_{partner}`.
A package is
installed by users with `pip install langchain-{partner}`, and the package members
A package is
installed by users with `pip install langchain-{partner}`, and the package members
can be imported with code like:
```python
@ -142,11 +143,11 @@ to the relevant `docs/docs/integrations` directory in the monorepo root.
### (If Necessary) Deprecate community integration
Note: this is only necessary if you're migrating an existing community integration into
a partner package. If the component you're integrating is net-new to LangChain (i.e.
Note: this is only necessary if you're migrating an existing community integration into
a partner package. If the component you're integrating is net-new to LangChain (i.e.
not already in the `community` package), you can skip this step.
Let's pretend we migrated our `ChatParrotLink` chat model from the community package to
Let's pretend we migrated our `ChatParrotLink` chat model from the community package to
the partner package. We would need to deprecate the old model in the community package.
We would do that by adding a `@deprecated` decorator to the old model as follows, in
@ -165,15 +166,15 @@ After our change, it would look like this:
from langchain_core._api.deprecation import deprecated
@ -8,4 +8,4 @@ import DocCardList from "@theme/DocCardList";
Example code for accomplishing common tasks with the LangChain Expression Language (LCEL). These examples show how to compose different Runnable (the core LCEL interface) components to achieve various tasks. If you're just getting acquainted with LCEL, the [Prompt + LLM](/docs/expression_language/cookbook/prompt_llm_parser) page is a good place to start.
The `langchain-community` package contains third-party integrations. It is automatically installed by `langchain`, but can also be used separately. Install with:
```bash
@ -37,6 +40,7 @@ pip install langchain-community
```
## LangChain core
The `langchain-core` package contains base abstractions that the rest of the LangChain ecosystem uses, along with the LangChain Expression Language. It is automatically installed by `langchain`, but can also be used separately. Install with:
```bash
@ -44,6 +48,7 @@ pip install langchain-core
```
## LangChain experimental
The `langchain-experimental` package holds experimental LangChain code, intended for research and experimental uses.
**LangChain** is a framework for developing applications powered by language models. It enables applications that:
- **Are context-aware**: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
- **Reason**: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
This framework consists of several parts.
- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.
- **[LangChain Templates](/docs/templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.
- **[LangServe](/docs/langserve)**: A library for deploying LangChain chains as a REST API.
- **[LangSmith](/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
import ThemedImage from '@theme/ThemedImage';
import ThemedImage from "@theme/ThemedImage";
<ThemedImage
alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
sources={{
light: '/svg/langchain_stack.svg',
dark: '/svg/langchain_stack_dark.svg',
light: "/svg/langchain_stack.svg",
dark: "/svg/langchain_stack_dark.svg",
}}
title="LangChain Framework Overview"
/>
Together, these products simplify the entire application lifecycle:
- **Develop**: Write your applications in LangChain/LangChain.js. Hit the ground running using Templates for reference.
- **Productionize**: Use LangSmith to inspect, test and monitor your chains, so that you can constantly improve and deploy with confidence.
- **Deploy**: Turn any chain into an API with LangServe.
@ -33,12 +36,14 @@ Together, these products simplify the entire application lifecycle:
## LangChain Libraries
The main value props of the LangChain packages are:
1. **Components**: composable tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones.
The LangChain libraries themselves are made up of several different packages.
- **`langchain-core`**: Base abstractions and LangChain Expression Language.
- **`langchain-community`**: Third party integrations.
- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
@ -66,39 +71,45 @@ LCEL is a declarative way to compose chains. LCEL was designed from day 1 to sup
- **[How-to](/docs/expression_language/how_to)**: Key features of LCEL
- **[Cookbook](/docs/expression_language/cookbook)**: Example code for accomplishing common tasks
## Modules
LangChain provides standard, extendable interfaces and integrations for the following modules:
#### [Model I/O](/docs/modules/model_io/)
Interface with language models
#### [Retrieval](/docs/modules/data_connection/)
Interface with application-specific data
#### [Agents](/docs/modules/agents/)
Let models choose which tools to use given high-level directives
Let models choose which tools to use given high-level directives
LangChain is part of a rich ecosystem of tools that integrate with our framework and build on top of it. Check out our growing list of [integrations](/docs/integrations/providers/).
We can now invoke it and ask the same question. It still won't know the answer, but it should respond in a more proper tone for a technical writer!
@ -231,15 +234,14 @@ chain.invoke({"input": "how can langsmith help with testing?"})
We've now successfully set up a basic LLM chain. We only touched on the basics of prompts, models, and output parsers - for a deeper dive into everything mentioned here, see [this section of documentation](/docs/modules/model_io).
## Retrieval Chain
In order to properly answer the original question ("how can langsmith help with testing?"), we need to provide additional context to the LLM.
We can do this via *retrieval*.
We can do this via _retrieval_.
Retrieval is useful when you have **too much data** to pass to the LLM directly.
You can then use a retriever to fetch only the most relevant pieces and pass those in.
In this process, we will look up relevant documents from a *Retriever* and then pass them into the prompt.
In this process, we will look up relevant documents from a _Retriever_ and then pass them into the prompt.
A Retriever can be backed by anything - a SQL table, the internet, etc - but in this instance we will populate a vector store and use that as a retriever. For more information on vectorstores, see [this documentation](/docs/modules/data_connection/vectorstores).
First, we need to load the data that we want to index. In order to do this, we will use the WebBaseLoader. This requires installing [BeautifulSoup](https://beautiful-soup-4.readthedocs.io/en/latest/):
@ -250,7 +252,6 @@ pip install beautifulsoup4
After that, we can import and use WebBaseLoader.
```python
from langchain_community.document_loaders import WebBaseLoader
You should see that this returns documents about testing in LangSmith. This is because the LLM generated a new query, combining the chat history with the follow up question.
Now that we have this new retriever, we can create a new chain to continue the conversation with these retrieved documents in mind.
@ -435,6 +438,7 @@ retrieval_chain.invoke({
"input": "Tell me how"
})
```
We can see that this gives a coherent answer - we've successfully turned our retrieval chain into a chatbot!
The search tool that we will use is [Tavily](/docs/integrations/retrievers/tavily). This will require an API key (they have generous free tier). After creating it on their platform, you need to set it as an environment variable:
```shell
export TAVILY_API_KEY=...
```
If you do not want to set up an API key, you can skip creating this tool.
Now that we have the tools, we can create an agent to use them. We will go over this pretty quickly - for a deeper dive into what exactly is going on, check out the [Agent's Getting Started documentation](/docs/modules/agents)
Install langchain hub first
```bash
pip install langchainhub
```
@ -530,7 +535,6 @@ agent_executor.invoke({
We've now successfully set up a basic agent. We only touched on the basics of agents - for a deeper dive into everything mentioned here, see [this section of documentation](/docs/modules/agents).
## Serving with LangServe
Now that we've built an application, we need to serve it. That's where LangServe comes in.
@ -539,6 +543,7 @@ LangServe helps developers deploy LangChain chains as a REST API. You do not nee
While the first part of this guide was intended to be run in a Jupyter Notebook, we will now move out of that. We will be creating a Python file and then interacting with it from the command line.
Install with:
```bash
pip install "langserve[all]"
```
@ -546,6 +551,7 @@ pip install "langserve[all]"
### Server
To create a server for our application we'll make a `serve.py` file. This will contain our logic for serving our application. It consists of three things:
1. The definition of our chain that we just built above
2. Our FastAPI app
3. A definition of a route from which to serve the chain, which is done with `langserve.add_routes`
@ -632,9 +638,11 @@ if __name__ == "__main__":
```
And that's it! If we execute this file:
```bash
python serve.py
```
we should see our chain being served at localhost:8000.
@ -4,8 +4,6 @@ If you're building with LLMs, at some point something will break, and you'll nee
Here are a few different tools and functionalities to aid in debugging.
## Tracing
Platforms with tracing capabilities like [LangSmith](/docs/langsmith/) and [WandB](/docs/integrations/providers/wandb_tracing) are the most comprehensive solutions for debugging. These platforms make it easy to not only log and visualize LLM apps, but also to actively debug, test and refine them.
@ -16,13 +14,12 @@ For anyone building production-grade LLM applications, we highly recommend using
## `set_debug` and `set_verbose`
If you're prototyping in Jupyter Notebooks or running Python scripts, it can be helpful to print out the intermediate steps of a Chain run.
If you're prototyping in Jupyter Notebooks or running Python scripts, it can be helpful to print out the intermediate steps of a Chain run.
There are a number of ways to enable printing at varying degrees of verbosity.
Let's suppose we have a simple agent, and want to visualize the actions it takes and tool outputs it receives. Without any debugging, here's what we see:
```python
from langchain.agents import AgentType, initialize_agent, load_tools
agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?")
```
@ -49,7 +45,6 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
Setting the global `debug` flag will cause all LangChain components with callback support (chains, models, agents, tools, retrievers) to print the inputs they receive and outputs they generate. This is the most verbose setting and will fully log raw inputs and outputs.
```python
from langchain.globals import set_debug
@ -62,7 +57,7 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
<CodeOutputBlocklang="python">
```
````
[chain/start] [1:RunTypeEnum.chain:AgentExecutor] Entering Chain run with input:
{
"input": "Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?"
@ -370,7 +365,7 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
'The director of the 2023 film Oppenheimer is Christopher Nolan and he is 52 years old. His age in days is approximately 18980 days.'
```
````
</CodeOutputBlock>
@ -380,7 +375,6 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
Setting the `verbose` flag will print out inputs and outputs in a slightly more readable format and will skip logging certain raw outputs (like the token usage stats for an LLM call) so that you can focus on application logic.
```python
from langchain.globals import set_verbose
@ -393,21 +387,21 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
<CodeOutputBlocklang="python">
```
````
> Entering new AgentExecutor chain...
> Entering new LLMChain chain...
Prompt after formatting:
Answer the following questions as best you can. You have access to the following tools:
duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
Calculator: Useful for when you need to answer questions about math.
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [duckduckgo_search, Calculator]
@ -416,28 +410,28 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
Thought:
> Finished chain.
First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
Action: duckduckgo_search
Action Input: "Director of the 2023 film Oppenheimer"
Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
Thought:
> Entering new LLMChain chain...
Prompt after formatting:
Answer the following questions as best you can. You have access to the following tools:
duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
Calculator: Useful for when you need to answer questions about math.
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [duckduckgo_search, Calculator]
@ -446,32 +440,32 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
Action: duckduckgo_search
Action Input: "Director of the 2023 film Oppenheimer"
Observation: Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb. In Christopher Nolan's new film, "Oppenheimer," Cillian Murphy stars as J. Robert ... 2023, 12:16 p.m. ET. ... including his role as the director of the Manhattan Engineer District, better ... J Robert Oppenheimer was the director of the secret Los Alamos Laboratory. It was established under US president Franklin D Roosevelt as part of the Manhattan Project to build the first atomic bomb. He oversaw the first atomic bomb detonation in the New Mexico desert in July 1945, code-named "Trinity". In this opening salvo of 2023's Oscar battle, Nolan has enjoined a star-studded cast for a retelling of the brilliant and haunted life of J. Robert Oppenheimer, the American physicist whose... Oppenheimer is a 2023 epic biographical thriller film written and directed by Christopher Nolan.It is based on the 2005 biography American Prometheus by Kai Bird and Martin J. Sherwin about J. Robert Oppenheimer, a theoretical physicist who was pivotal in developing the first nuclear weapons as part of the Manhattan Project and thereby ushering in the Atomic Age.
Thought:
> Finished chain.
The director of the 2023 film Oppenheimer is Christopher Nolan. Now I need to find out his birth date to calculate his age.
Action: duckduckgo_search
Action Input: "Christopher Nolan birth date"
Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. July 2023 sees the release of Christopher Nolan's new film, Oppenheimer, his first movie since 2020's Tenet and his split from Warner Bros. Billed as an epic thriller about "the man who ...
Thought:
> Entering new LLMChain chain...
Prompt after formatting:
Answer the following questions as best you can. You have access to the following tools:
duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
Calculator: Useful for when you need to answer questions about math.
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [duckduckgo_search, Calculator]
@ -480,9 +474,9 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
Action: duckduckgo_search
@ -493,19 +487,19 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
Action Input: "Christopher Nolan birth date"
Observation: July 30, 1970 (age 52) London England Notable Works: "Dunkirk" "Tenet" "The Prestige" See all related content → Recent News Jul. 13, 2023, 11:11 AM ET (AP) Cillian Murphy, playing Oppenheimer, finally gets to lead a Christopher Nolan film Christopher Edward Nolan CBE (born 30 July 1970) is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have grossed $5 billion worldwide. The recipient of many accolades, he has been nominated for five Academy Awards, five BAFTA Awards and six Golden Globe Awards. Christopher Nolan is currently 52 according to his birthdate July 30, 1970 Sun Sign Leo Born Place Westminster, London, England, United Kingdom Residence Los Angeles, California, United States Nationality Education Chris attended Haileybury and Imperial Service College, in Hertford Heath, Hertfordshire. Christopher Nolan's next movie will study the man who developed the atomic bomb, J. Robert Oppenheimer. Here's the release date, plot, trailers & more. July 2023 sees the release of Christopher Nolan's new film, Oppenheimer, his first movie since 2020's Tenet and his split from Warner Bros. Billed as an epic thriller about "the man who ...
Thought:
> Finished chain.
Christopher Nolan was born on July 30, 1970. Now I need to calculate his age in 2023 and then convert it into days.
Action: Calculator
Action Input: (2023 - 1970) * 365
> Entering new LLMMathChain chain...
(2023 - 1970) * 365
> Entering new LLMChain chain...
Prompt after formatting:
Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.
Question: ${Question with math problem.}
```text
${single line mathematical expression that solves the problem}
@ -515,9 +509,9 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
${Output of running the code}
```
Answer: ${Answer}
Begin.
Question: What is 37593 * 67?
```text
37593 * 67
@ -527,7 +521,7 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
2518731
```
Answer: 2518731
Question: 37593^(1/5)
```text
37593**(1/5)
@ -537,31 +531,31 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
8.222831614237718
```
Answer: 8.222831614237718
Question: (2023 - 1970) * 365
> Finished chain.
```text
(2023 - 1970) * 365
```
...numexpr.evaluate("(2023 - 1970) * 365")...
Answer: 19345
> Finished chain.
Observation: Answer: 19345
Thought:
> Entering new LLMChain chain...
Prompt after formatting:
Answer the following questions as best you can. You have access to the following tools:
duckduckgo_search: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.
Calculator: Useful for when you need to answer questions about math.
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [duckduckgo_search, Calculator]
@ -570,9 +564,9 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: Who directed the 2023 film Oppenheimer and what is their age? What is their age in days (assume 365 days per year)?
Thought:First, I need to find out who directed the film Oppenheimer in 2023 and their birth date to calculate their age.
Action: duckduckgo_search
@ -587,16 +581,16 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
Action Input: (2023 - 1970) * 365
Observation: Answer: 19345
Thought:
> Finished chain.
I now know the final answer
Final Answer: The director of the 2023 film Oppenheimer is Christopher Nolan and he is 53 years old in 2023. His age in days is 19345 days.
> Finished chain.
'The director of the 2023 film Oppenheimer is Christopher Nolan and he is 53 years old in 2023. His age in days is 19345 days.'
```
````
</CodeOutputBlock>
@ -606,12 +600,11 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
You can also scope verbosity down to a single object, in which case only the inputs and outputs to that object are printed (along with any additional callbacks calls made specifically by that object).
```python
# Passing verbose=True to initialize_agent will pass that along to the AgentExecutor (which is a Chain).
agent = initialize_agent(
tools,
llm,
tools,
llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True,
)
@ -643,7 +636,7 @@ agent.run("Who directed the 2023 film Oppenheimer and what is their age? What is
Observation: Answer: 19345
Thought:I now know the final answer
Final Answer: The director of the 2023 film Oppenheimer is Christopher Nolan. He is 53 years old in 2023, which is approximately 19345 days.
In today's fast-paced technological landscape, the use of Large Language Models (LLMs) is rapidly expanding. As a result, it is crucial for developers to understand how to effectively deploy these models in production environments. LLM interfaces typically fall into two categories:
In this scenario, most of the computational burden is handled by the LLM providers, while LangChain simplifies the implementation of business logic around these services. This approach includes features such as prompt templating, chat message generation, caching, vector embedding database creation, preprocessing, etc.
In this scenario, most of the computational burden is handled by the LLM providers, while LangChain simplifies the implementation of business logic around these services. This approach includes features such as prompt templating, chat message generation, caching, vector embedding database creation, preprocessing, etc.
- **Case 2: Self-hosted Open-Source Models**
Alternatively, developers can opt to use smaller, yet comparably capable, self-hosted open-source LLM models. This approach can significantly decrease costs, latency, and privacy concerns associated with transferring data to external LLM providers.
Alternatively, developers can opt to use smaller, yet comparably capable, self-hosted open-source LLM models. This approach can significantly decrease costs, latency, and privacy concerns associated with transferring data to external LLM providers.
Regardless of the framework that forms the backbone of your product, deploying LLM applications comes with its own set of challenges. It's vital to understand the trade-offs and key considerations when evaluating serving frameworks.
@ -48,28 +48,23 @@ Monitoring forms an integral part of any system running in a production environm
Your application may encounter errors such as exceptions in your model inference or business logic code, causing failures and disrupting traffic. Other potential issues could arise from the machine running your application, such as unexpected hardware breakdowns or loss of spot-instances during high-demand periods. One way to mitigate these risks is by increasing redundancy through replica scaling and implementing recovery mechanisms for failed replicas. However, model replicas aren't the only potential points of failure. It's essential to build resilience against various failures that could occur at any point in your stack.
### Zero down time upgrade
System upgrades are often necessary but can result in service disruptions if not handled correctly. One way to prevent downtime during upgrades is by implementing a smooth transition process from the old version to the new one. Ideally, the new version of your LLM service is deployed, and traffic gradually shifts from the old to the new version, maintaining a constant QPS throughout the process.
### Load balancing
Load balancing, in simple terms, is a technique to distribute work evenly across multiple computers, servers, or other resources to optimize the utilization of the system, maximize throughput, minimize response time, and avoid overload of any single resource. Think of it as a traffic officer directing cars (requests) to different roads (servers) so that no single road becomes too congested.
There are several strategies for load balancing. For example, one common method is the *Round Robin* strategy, where each request is sent to the next server in line, cycling back to the first when all servers have received a request. This works well when all servers are equally capable. However, if some servers are more powerful than others, you might use a *Weighted Round Robin* or *Least Connections* strategy, where more requests are sent to the more powerful servers, or to those currently handling the fewest active requests. Let's imagine you're running a LLM chain. If your application becomes popular, you could have hundreds or even thousands of users asking questions at the same time. If one server gets too busy (high load), the load balancer would direct new requests to another server that is less busy. This way, all your users get a timely response and the system remains stable.
There are several strategies for load balancing. For example, one common method is the _Round Robin_ strategy, where each request is sent to the next server in line, cycling back to the first when all servers have received a request. This works well when all servers are equally capable. However, if some servers are more powerful than others, you might use a _Weighted Round Robin_ or _Least Connections_ strategy, where more requests are sent to the more powerful servers, or to those currently handling the fewest active requests. Let's imagine you're running a LLM chain. If your application becomes popular, you could have hundreds or even thousands of users asking questions at the same time. If one server gets too busy (high load), the load balancer would direct new requests to another server that is less busy. This way, all your users get a timely response and the system remains stable.
## Maintaining Cost-Efficiency and Scalability
Deploying LLM services can be costly, especially when you're handling a large volume of user interactions. Charges by LLM providers are usually based on tokens used, making a chat system inference on these models potentially expensive. However, several strategies can help manage these costs without compromising the quality of the service.
### Self-hosting models
Several smaller and open-source LLMs are emerging to tackle the issue of reliance on LLM providers. Self-hosting allows you to maintain similar quality to LLM provider models while managing costs. The challenge lies in building a reliable, high-performing LLM serving system on your own machines.
Several smaller and open-source LLMs are emerging to tackle the issue of reliance on LLM providers. Self-hosting allows you to maintain similar quality to LLM provider models while managing costs. The challenge lies in building a reliable, high-performing LLM serving system on your own machines.
### Resource Management and Auto-Scaling
@ -87,10 +82,7 @@ When self-hosting your models, you should consider independent scaling. For exam
In the context of Large Language Models, batching requests can enhance efficiency by better utilizing your GPU resources. GPUs are inherently parallel processors, designed to handle multiple tasks simultaneously. If you send individual requests to the model, the GPU might not be fully utilized as it's only working on a single task at a time. On the other hand, by batching requests together, you're allowing the GPU to work on multiple tasks at once, maximizing its utilization and improving inference speed. This not only leads to cost savings but can also improve the overall latency of your LLM service.
In summary, managing costs while scaling your LLM services requires a strategic approach. Utilizing self-hosting models, managing resources effectively, employing auto-scaling, using spot instances, independently scaling models, and batching requests are key strategies to consider. Open-source libraries such as Ray Serve and BentoML are designed to deal with these complexities.
In summary, managing costs while scaling your LLM services requires a strategic approach. Utilizing self-hosting models, managing resources effectively, employing auto-scaling, using spot instances, independently scaling models, and batching requests are key strategies to consider. Open-source libraries such as Ray Serve and BentoML are designed to deal with these complexities.
## Ensuring Rapid Iteration
@ -104,12 +96,10 @@ Deploying systems like LangChain demands the ability to piece together different
Many hosted solutions are restricted to a single cloud provider, which can limit your options in today's multi-cloud world. Depending on where your other infrastructure components are built, you might prefer to stick with your chosen cloud provider.
## Infrastructure as Code (IaC)
Rapid iteration also involves the ability to recreate your infrastructure quickly and reliably. This is where Infrastructure as Code (IaC) tools like Terraform, CloudFormation, or Kubernetes YAML files come into play. They allow you to define your infrastructure in code files, which can be version controlled and quickly deployed, enabling faster and more reliable iterations.
## CI/CD
In a fast-paced environment, implementing CI/CD pipelines can significantly speed up the iteration process. They help automate the testing and deployment of your LLM applications, reducing the risk of errors and enabling faster feedback and iteration.
Comparison evaluators in LangChain help measure two different chains or LLM outputs. These evaluators are helpful for comparative analyses, such as A/B testing between two language models, or comparing different versions of the same model. They can also be useful for things like generating preference scores for ai-assisted reinforcement learning.
@ -25,4 +26,3 @@ Detailed information about creating custom evaluators and the available built-in
@ -2,7 +2,7 @@ import DocCardList from "@theme/DocCardList";
# Evaluation
Building applications with language models involves many moving parts. One of the most critical components is ensuring that the outcomes produced by your models are reliable and useful across a broad array of inputs, and that they work well with your application's other software components. Ensuring reliability usually boils down to some combination of application design, testing & evaluation, and runtime checks.
Building applications with language models involves many moving parts. One of the most critical components is ensuring that the outcomes produced by your models are reliable and useful across a broad array of inputs, and that they work well with your application's other software components. Ensuring reliability usually boils down to some combination of application design, testing & evaluation, and runtime checks.
The guides in this section review the APIs and functionality LangChain provides to help you better evaluate your applications. Evaluation and testing are both critical when thinking about deploying LLM applications, since production environments require repeatable and useful outcomes.
@ -20,7 +20,6 @@ We also are working to share guides and cookbooks that demonstrate how to use th
- [Chain Comparisons](/docs/guides/evaluation/examples/comparisons): This example uses a comparison evaluator to predict the preferred output. It reviews ways to measure confidence intervals to select statistically significant differences in aggregate preference scores across different models or prompts.
## LangSmith Evaluation
LangSmith provides an integrated evaluation and tracing framework that allows you to check for regressions, compare systems, and easily identify and fix any sources of errors and performance issues. Check out the docs on [LangSmith Evaluation](https://docs.smith.langchain.com/evaluation) and additional [cookbooks](https://docs.smith.langchain.com/cookbook) for more detailed information on evaluating your applications.
@ -31,7 +30,7 @@ Your application quality is a function both of the LLM you choose and the prompt
- Agent tool use
- Retrieval-augmented question-answering
- Structured Extraction
- Structured Extraction
Check out the docs for examples and leaderboard information.
A string evaluator is a component within LangChain designed to assess the performance of a language model by comparing its generated outputs (predictions) to a reference string or an input. This comparison is a crucial step in the evaluation of language models, providing a measure of the accuracy or quality of the generated text.
Trajectory Evaluators in LangChain provide a more holistic approach to evaluating an agent. These evaluators assess the full sequence of actions taken by an agent and their corresponding responses, which we refer to as the "trajectory". This allows you to better measure an agent's effectiveness and capabilities.
@ -25,4 +26,3 @@ For a deeper dive into the implementation and use of Trajectory Evaluators, refe
As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2.
* Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
* During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2.
- Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
- During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
User can either pin to pydantic v1, and upgrade their code in one go once LangChain has migrated to v2 internally, or they can start a partial migration to v2, but must avoid mixing v1 and v2 code for LangChain.
@ -18,7 +19,7 @@ the case of inheritance and in the case of passing objects to LangChain.
**Example 1: Extending via inheritance**
**YES**
**YES**
```python
from pydantic.v1 import root_validator, validator
@ -33,7 +34,7 @@ class CustomTool(BaseTool): # BaseTool is v1 code
@classmethod
def validate_x(cls, x: int) -> int:
return 1
CustomTool(
name='custom_tool',
@ -44,7 +45,7 @@ CustomTool(
Mixing Pydantic v2 primitives with Pydantic v1 primitives can raise cryptic errors
**NO**
**NO**
```python
from pydantic import Field, field_validator # pydantic v2
@ -59,9 +60,9 @@ class CustomTool(BaseTool): # BaseTool is v1 code
@ -350,7 +342,6 @@ constitutional_chain({"question":"How can I steal kittens?"})
We can also see that the chain recognizes when no revision is necessary.
```python
good_qa_prompt = PromptTemplate(
template="""You are good and must only give good and ethical answers. If someone asks you how to do something illegal, make sure you respond in an ethical and legal way.
@ -376,7 +367,6 @@ good_qa_chain.run(question="How can I steal kittens?")
@ -4,6 +4,6 @@ One of the key concerns with using LLMs is that they may generate harmful or une
- [Amazon Comprehend moderation chain](/docs/guides/safety/amazon_comprehend_chain): Use [Amazon Comprehend](https://aws.amazon.com/comprehend/) to detect and handle Personally Identifiable Information (PII) and toxicity.
- [Constitutional chain](/docs/guides/safety/constitutional_chain): Prompt the model with a set of principles which should guide the model behavior.
- [Hugging Face prompt injection identification](/docs/guides/safety/hugging_face_prompt_injection): Detect and handle prompt injection attacks.
- [Hugging Face prompt injection identification](/docs/guides/safety/hugging_face_prompt_injection): Detect and handle prompt injection attacks.
- [Logical Fallacy chain](/docs/guides/safety/logical_fallacy_chain): Checks the model output against logical fallacies to correct any deviation.
- [Moderation chain](/docs/guides/safety/moderation): Check if any output text is harmful and flag it.
@ -4,18 +4,17 @@ This example shows how to remove logical fallacies from model output.
## Logical Fallacies
`Logical fallacies` are flawed reasoning or false arguments that can undermine the validity of a model's outputs.
`Logical fallacies` are flawed reasoning or false arguments that can undermine the validity of a model's outputs.
Examples include circular reasoning, false
dichotomies, ad hominem attacks, etc. Machine learning models are optimized to perform well on specific metrics like accuracy, perplexity, or loss. However,
dichotomies, ad hominem attacks, etc. Machine learning models are optimized to perform well on specific metrics like accuracy, perplexity, or loss. However,
optimizing for metrics alone does not guarantee logically sound reasoning.
Language models can learn to exploit flaws in reasoning to generate plausible-sounding but logically invalid arguments. When models rely on fallacies, their outputs become unreliable and untrustworthy, even if they achieve high scores on metrics. Users cannot depend on such outputs. Propagating logical fallacies can spread misinformation, confuse users, and lead to harmful real-world consequences when models are deployed in products or services.
Language models can learn to exploit flaws in reasoning to generate plausible-sounding but logically invalid arguments. When models rely on fallacies, their outputs become unreliable and untrustworthy, even if they achieve high scores on metrics. Users cannot depend on such outputs. Propagating logical fallacies can spread misinformation, confuse users, and lead to harmful real-world consequences when models are deployed in products or services.
Monitoring and testing specifically for logical flaws is challenging unlike other quality issues. It requires reasoning about arguments rather than pattern matching.
Therefore, it is crucial that model developers proactively address logical fallacies after optimizing metrics. Specialized techniques like causal modeling, robustness testing, and bias mitigation can help avoid flawed reasoning. Overall, allowing logical flaws to persist makes models less safe and ethical. Eliminating fallacies ensures model outputs remain logically valid and aligned with human reasoning. This maintains user trust and mitigates risks.
Therefore, it is crucial that model developers proactively address logical fallacies after optimizing metrics. Specialized techniques like causal modeling, robustness testing, and bias mitigation can help avoid flawed reasoning. Overall, allowing logical flaws to persist makes models less safe and ethical. Eliminating fallacies ensures model outputs remain logically valid and aligned with human reasoning. This maintains user trust and mitigates risks.
## Example
@ -51,7 +50,6 @@ misleading_chain.run(question="How do I know the earth is round?")
This notebook walks through examples of how to use a moderation chain, and several common ways for doing so.
Moderation chains are useful for detecting text that could be hateful, violent, etc. This can be useful to apply on both user input, but also on the output of a Language Model.
Some API providers, like OpenAI, [specifically prohibit](https://beta.openai.com/docs/usage-policies/use-case-policy) you, or your end users, from generating some
types of harmful content. To comply with this (and to just generally prevent your application from being harmful)
you may often want to append a moderation chain to any LLMChains, in order to make sure any output
This notebook walks through examples of how to use a moderation chain, and several common ways for doing so.
Moderation chains are useful for detecting text that could be hateful, violent, etc. This can be useful to apply on both user input, but also on the output of a Language Model.
Some API providers, like OpenAI, [specifically prohibit](https://beta.openai.com/docs/usage-policies/use-case-policy) you, or your end users, from generating some
types of harmful content. To comply with this (and to just generally prevent your application from being harmful)
you may often want to append a moderation chain to any LLMChains, in order to make sure any output
the LLM generates is not harmful.
If the content passed into the moderation chain is harmful, there is not one best way to handle it,
it probably depends on your application. Sometimes you may want to throw an error in the Chain
(and have your application handle that). Other times, you may want to return something to
If the content passed into the moderation chain is harmful, there is not one best way to handle it,
it probably depends on your application. Sometimes you may want to throw an error in the Chain
(and have your application handle that). Other times, you may want to return something to
the user explaining that the text was harmful. There could be other ways to handle it.
We will cover all these ways in this walkthrough.
@ -18,9 +18,6 @@ We'll show:
1. How to run any piece of text through a moderation chain.
2. How to append a Moderation chain to an LLMChain.
```python
from langchain_openai import OpenAI
from langchain.chains import OpenAIModerationChain, SequentialChain, LLMChain, SimpleSequentialChain
@ -29,10 +26,9 @@ from langchain.prompts import PromptTemplate
## How to use the moderation chain
Here's an example of using the moderation chain with default settings (will return a string
Here's an example of using the moderation chain with default settings (will return a string
explaining stuff was flagged).
```python
moderation_chain = OpenAIModerationChain()
@ -47,7 +43,6 @@ moderation_chain.run("This is okay")
</CodeOutputBlock>
```python
moderation_chain.run("I will kill you")
```
@ -62,7 +57,6 @@ moderation_chain.run("I will kill you")
Here's an example of using the moderation chain to throw an error.
Now let's walk through an example of using it with an LLMChain which has multiple inputs (a bit more tricky because we can't use the SimpleSequentialChain)
>[LLMonitor](https://llmonitor.com?utm_source=langchain&utm_medium=py&utm_campaign=docs) is an open-source observability platform that provides cost and usage analytics, user tracking, tracing and evaluation tools.
>[LLMonitor](https://llmonitor.com?utm_source=langchain&utm_medium=py&utm_campaign=docs) is an open-source observability platform that provides cost and usage analytics, user tracking, tracing and evaluation tools.
User tracking allows you to identify your users, track their cost, conversations and more.
```python
@ -112,6 +113,7 @@ with identify("user-123"):
with identify("user-456", user_props={"email": "user456@test.com"}):
agen.run("Who is Leo DiCaprio's girlfriend?")
```
## Support
For any question or issue with integration you can reach out to the LLMonitor team on [Discord](http://discord.com/invite/8PafSG58kK) or via [email](mailto:vince@llmonitor.com).
> interactive log analytics, real-time application monitoring, website search, and more. `OpenSearch` is
> an open source,
> distributed search and analytics suite derived from `Elasticsearch`. `Amazon OpenSearch Service` offers the
> latest versions of `OpenSearch`, support for many versions of `Elasticsearch`, as well as
> visualization capabilities powered by `OpenSearch Dashboards` and `Kibana`.
We need to install several python libraries.
@ -137,7 +137,7 @@ from langchain_community.vectorstores import OpenSearchVectorSearch
### Amazon DocumentDB Vector Search
>[Amazon DocumentDB (with MongoDB Compatibility)](https://docs.aws.amazon.com/documentdb/) makes it easy to set up, operate, and scale MongoDB-compatible databases in the cloud.
>[Amazon DocumentDB (with MongoDB Compatibility)](https://docs.aws.amazon.com/documentdb/) makes it easy to set up, operate, and scale MongoDB-compatible databases in the cloud.
> With Amazon DocumentDB, you can run the same application code and use the same drivers and tools that you use with MongoDB.
> Vector search for Amazon DocumentDB combines the flexibility and rich querying capability of a JSON-based document database with the power of vector search.
@ -167,14 +167,14 @@ from langchain.vectorstores import DocumentDBVectorSearch
### Amazon Kendra
> [Amazon Kendra](https://docs.aws.amazon.com/kendra/latest/dg/what-is-kendra.html) is an intelligent search service
> provided by `Amazon Web Services` (`AWS`). It utilizes advanced natural language processing (NLP) and machine
> learning algorithms to enable powerful search capabilities across various data sources within an organization.
> `Kendra` is designed to help users find the information they need quickly and accurately,
> [Amazon Kendra](https://docs.aws.amazon.com/kendra/latest/dg/what-is-kendra.html) is an intelligent search service
> provided by `Amazon Web Services` (`AWS`). It utilizes advanced natural language processing (NLP) and machine
> learning algorithms to enable powerful search capabilities across various data sources within an organization.
> `Kendra` is designed to help users find the information they need quickly and accurately,
> improving productivity and decision-making.
> With `Kendra`, we can search across a wide range of content types, including documents, FAQs, knowledge bases,
> manuals, and websites. It supports multiple languages and can understand complex queries, synonyms, and
> With `Kendra`, we can search across a wide range of content types, including documents, FAQs, knowledge bases,
> manuals, and websites. It supports multiple languages and can understand complex queries, synonyms, and
> contextual meanings to provide highly relevant search results.
We need to install the `boto3` library.
@ -191,8 +191,8 @@ from langchain.retrievers import AmazonKendraRetriever
### Amazon Bedrock (Knowledge Bases)
> [Knowledge bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) is an
> `Amazon Web Services` (`AWS`) offering which lets you quickly build RAG applications by using your
> [Knowledge bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) is an
> `Amazon Web Services` (`AWS`) offering which lets you quickly build RAG applications by using your
> private data to customize foundation model response.
We need to install the `boto3` library.
@ -211,10 +211,10 @@ from langchain.retrievers import AmazonKnowledgeBasesRetriever
### AWS Lambda
>[`Amazon AWS Lambda`](https://aws.amazon.com/pm/lambda/) is a serverless computing service provided by
> `Amazon Web Services` (`AWS`). It helps developers to build and run applications and services without
> provisioning or managing servers. This serverless architecture enables you to focus on writing and
> deploying code, while AWS automatically takes care of scaling, patching, and managing the
>[`Amazon AWS Lambda`](https://aws.amazon.com/pm/lambda/) is a serverless computing service provided by
> `Amazon Web Services` (`AWS`). It helps developers to build and run applications and services without
> provisioning or managing servers. This serverless architecture enables you to focus on writing and
> deploying code, while AWS automatically takes care of scaling, patching, and managing the
> infrastructure required to run your applications.
We need to install `boto3` python library.
@ -229,10 +229,10 @@ See a [usage example](/docs/integrations/tools/awslambda).
@ -36,7 +36,6 @@ See a [usage example](/docs/integrations/llms/google_vertex_ai_palm#vertex-model
from langchain_google_vertexai import VertexAIModelGarden
```
## Chat models
### Google Generative AI
@ -175,7 +174,7 @@ from langchain_community.document_loaders import BigQueryLoader
### Bigtable
> [Google Cloud Bigtable](https://cloud.google.com/bigtable/docs) is Google's fully managed NoSQL Big Data database service in Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-bigtable
@ -190,7 +189,7 @@ from langchain_google_bigtable import BigtableLoader
### Cloud SQL for MySQL
> [Google Cloud SQL for MySQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your MySQL relational databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-mysql
@ -205,7 +204,7 @@ from langchain_google_cloud_sql_mysql import MySQLEngine, MySQLDocumentLoader
### Cloud SQL for SQL Server
> [Google Cloud SQL for SQL Server](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your SQL Server databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-mssql
@ -220,7 +219,7 @@ from langchain_google_cloud_sql_mssql import MSSQLEngine, MSSQLLoader
### Cloud SQL for PostgreSQL
> [Google Cloud SQL for PostgreSQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-pg
@ -234,7 +233,7 @@ from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgreSQLLoader
### Cloud Storage
>[Cloud Storage](https://en.wikipedia.org/wiki/Google_Cloud_Storage) is a managed service for storing unstructured data in Google Cloud.
>[Cloud Storage](https://en.wikipedia.org/wiki/Google_Cloud_Storage) is a managed service for storing unstructured data in Google Cloud.
We need to install `google-cloud-storage` python package.
@ -249,6 +248,7 @@ See a [usage example](/docs/integrations/document_loaders/google_cloud_storage_d
```python
from langchain_community.document_loaders import GCSDirectoryLoader
```
See a [usage example](/docs/integrations/document_loaders/google_cloud_storage_file).
```python
@ -258,8 +258,8 @@ from langchain_community.document_loaders import GCSFileLoader
### El Carro for Oracle Workloads
> Google [El Carro Oracle Operator](https://github.com/GoogleCloudPlatform/elcarro-oracle-operator)
offers a way to run Oracle databases in Kubernetes as a portable, open source,
community driven, no vendor lock-in container orchestration system.
> offers a way to run Oracle databases in Kubernetes as a portable, open source,
> community driven, no vendor lock-in container orchestration system.
```bash
pip install langchain-google-el-carro
@ -273,7 +273,7 @@ from langchain_google_el_carro import ElCarroLoader
### Google Drive
>[Google Drive](https://en.wikipedia.org/wiki/Google_Drive) is a file storage and synchronization service developed by Google.
>[Google Drive](https://en.wikipedia.org/wiki/Google_Drive) is a file storage and synchronization service developed by Google.
Currently, only `Google Docs` are supported.
@ -292,7 +292,7 @@ from langchain_community.document_loaders import GoogleDriveLoader
### Firestore (Native Mode)
> [Google Cloud Firestore](https://cloud.google.com/firestore/docs/) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-firestore
@ -308,7 +308,7 @@ from langchain_google_firestore import FirestoreLoader
> [Google Cloud Firestore in Datastore mode](https://cloud.google.com/datastore/docs) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
> Firestore is the newest version of Datastore and introduces several improvements over Datastore.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-datastore
@ -323,7 +323,7 @@ from langchain_google_datastore import DatastoreLoader
### Memorystore for Redis
> [Google Cloud Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis) is a fully managed Redis service for Google Cloud. Applications running on Google Cloud can achieve extreme performance by leveraging the highly scalable, available, secure Redis service without the burden of managing complex Redis deployments.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-memorystore-redis
@ -338,7 +338,7 @@ from langchain_google_memorystore_redis import MemorystoreLoader
### Spanner
> [Google Cloud Spanner](https://cloud.google.com/spanner/docs) is a fully managed, mission-critical, relational database service on Google Cloud that offers transactional consistency at global scale, automatic, synchronous replication for high availability, and support for two SQL dialects: GoogleSQL (ANSI 2011 with extensions) and PostgreSQL.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-spanner
@ -372,7 +372,7 @@ from langchain_community.document_loaders import GoogleSpeechToTextLoader
### Document AI
>[Google Cloud Document AI](https://cloud.google.com/document-ai/docs/overview) is a Google Cloud
>[Google Cloud Document AI](https://cloud.google.com/document-ai/docs/overview) is a Google Cloud
> service that transforms unstructured data from documents into structured data, making it easier
> to understand, analyze, and consume.
@ -459,7 +459,7 @@ from langchain.vectorstores import BigQueryVectorSearch
### Memorystore for Redis
> [Google Cloud Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis) is a fully managed Redis service for Google Cloud. Applications running on Google Cloud can achieve extreme performance by leveraging the highly scalable, available, secure Redis service without the burden of managing complex Redis deployments.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-memorystore-redis
@ -474,7 +474,7 @@ from langchain_google_memorystore_redis import RedisVectorStore
### Spanner
> [Google Cloud Spanner](https://cloud.google.com/spanner/docs) is a fully managed, mission-critical, relational database service on Google Cloud that offers transactional consistency at global scale, automatic, synchronous replication for high availability, and support for two SQL dialects: GoogleSQL (ANSI 2011 with extensions) and PostgreSQL.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-spanner
@ -489,7 +489,7 @@ from langchain_google_spanner import SpannerVectorStore
### Cloud SQL for PostgreSQL
> [Google Cloud SQL for PostgreSQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-pg
@ -522,12 +522,12 @@ from langchain_google_vertexai import VectorSearchVectorStore
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) is a Google Cloud service that enables developers to
>[Google Cloud Text-to-Speech](https://cloud.google.com/text-to-speech) is a Google Cloud service that enables developers to
> synthesize natural-sounding speech with 100+ voices, available in multiple languages and variants.
> It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks
> to deliver the highest fidelity possible.
@ -703,7 +703,7 @@ from langchain_community.utilities.google_scholar import GoogleScholarAPIWrapper
- Set up a Custom Search Engine, following [these instructions](https://stackoverflow.com/questions/37083058/programmatically-searching-google-in-python-using-custom-search)
- Get an API Key and Custom Search Engine ID from the previous step, and set them as environment variables
`GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively.
`GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively.
```python
from langchain_community.utilities import GoogleSearchAPIWrapper
@ -738,7 +738,7 @@ from langchain_community.utilities.google_trends import GoogleTrendsAPIWrapper
### GMail
> [Google Gmail](https://en.wikipedia.org/wiki/Gmail) is a free email service provided by Google.
This toolkit works with emails through the `Gmail API`.
> This toolkit works with emails through the `Gmail API`.
We need to install several python packages.
@ -773,7 +773,7 @@ from langchain_google_alloydb_pg import AlloyDBEngine, AlloyDBChatMessageHistory
### Cloud SQL for PostgreSQL
> [Cloud SQL for PostgreSQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud.
See [usage example](/docs/integrations/memory/google_sql_pg).
```python
from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgreSQLChatMessageHistory
```
@ -789,7 +788,7 @@ from langchain_google_cloud_sql_pg import PostgreSQLEngine, PostgreSQLChatMessag
### Cloud SQL for MySQL
> [Cloud SQL for MySQL](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your MySQL relational databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-mysql
@ -804,7 +803,7 @@ from langchain_google_cloud_sql_mysql import MySQLEngine, MySQLChatMessageHistor
### Cloud SQL for SQL Server
> [Cloud SQL for SQL Server](https://cloud.google.com/sql) is a fully-managed database service that helps you set up, maintain, manage, and administer your SQL Server databases on Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-cloud-sql-mssql
@ -819,7 +818,7 @@ from langchain_google_cloud_sql_mssql import MSSQLEngine, MSSQLChatMessageHistor
### Spanner
> [Google Cloud Spanner](https://cloud.google.com/spanner/docs) is a fully managed, mission-critical, relational database service on Google Cloud that offers transactional consistency at global scale, automatic, synchronous replication for high availability, and support for two SQL dialects: GoogleSQL (ANSI 2011 with extensions) and PostgreSQL.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-spanner
@ -834,7 +833,7 @@ from langchain_google_spanner import SpannerChatMessageHistory
### Memorystore for Redis
> [Google Cloud Memorystore for Redis](https://cloud.google.com/memorystore/docs/redis) is a fully managed Redis service for Google Cloud. Applications running on Google Cloud can achieve extreme performance by leveraging the highly scalable, available, secure Redis service without the burden of managing complex Redis deployments.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-memorystore-redis
@ -849,7 +848,7 @@ from langchain_google_memorystore_redis import MemorystoreChatMessageHistory
### Bigtable
> [Google Cloud Bigtable](https://cloud.google.com/bigtable/docs) is Google's fully managed NoSQL Big Data database service in Google Cloud.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-bigtable
@ -864,7 +863,7 @@ from langchain_google_bigtable import BigtableChatMessageHistory
### Firestore (Native Mode)
> [Google Cloud Firestore](https://cloud.google.com/firestore/docs/) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-firestore
@ -880,7 +879,7 @@ from langchain_google_firestore import FirestoreChatMessageHistory
> [Google Cloud Firestore in Datastore mode](https://cloud.google.com/datastore/docs) is a NoSQL document database built for automatic scaling, high performance, and ease of application development.
> Firestore is the newest version of Datastore and introduces several improvements over Datastore.
Install the python package:
> Install the python package:
```bash
pip install langchain-google-datastore
@ -895,8 +894,8 @@ from langchain_google_datastore import DatastoreChatMessageHistory
### El Carro: The Oracle Operator for Kubernetes
> Google [El Carro Oracle Operator for Kubernetes](https://github.com/GoogleCloudPlatform/elcarro-oracle-operator)
offers a way to run `Oracle` databases in `Kubernetes` as a portable, open source,
community driven, no vendor lock-in container orchestration system.
> offers a way to run `Oracle` databases in `Kubernetes` as a portable, open source,
> community driven, no vendor lock-in container orchestration system.
```bash
pip install langchain-google-el-carro
@ -913,7 +912,7 @@ from langchain_google_el_carro import ElCarroChatMessageHistory
### GMail
> [Gmail](https://en.wikipedia.org/wiki/Gmail) is a free email service provided by Google.
This loader works with emails through the `Gmail API`.
> This loader works with emails through the `Gmail API`.
We need to install several python packages.
@ -931,7 +930,7 @@ from langchain_community.chat_loaders.gmail import GMailLoader
### SearchApi
>[SearchApi](https://www.searchapi.io/) provides a 3rd-party API to access Google search results, YouTube search & transcripts, and other Google-related engines.
>[SearchApi](https://www.searchapi.io/) provides a 3rd-party API to access Google search results, YouTube search & transcripts, and other Google-related engines.
See [usage examples and authorization instructions](/docs/integrations/tools/searchapi).
@ -941,7 +940,7 @@ from langchain_community.utilities import SearchApiAPIWrapper
### SerpApi
>[SerpApi](https://serpapi.com/) provides a 3rd-party API to access Google search results.
>[SerpApi](https://serpapi.com/) provides a 3rd-party API to access Google search results.
See a [usage example and authorization instructions](/docs/integrations/tools/serpapi).
@ -959,9 +958,9 @@ from langchain_community.utilities import GoogleSerperAPIWrapper
### YouTube
>[YouTube Search](https://github.com/joetats/youtube_search) package searches `YouTube` videos avoiding using their heavily rate-limited API.
>[YouTube Search](https://github.com/joetats/youtube_search) package searches `YouTube` videos avoiding using their heavily rate-limited API.
>
>It uses the form on the YouTube homepage and scrapes the resulting page.
>It uses the form on the YouTube homepage and scrapes the resulting page.
We need to install a python package.
@ -977,7 +976,7 @@ from langchain.tools import YouTubeSearchTool
### YouTube audio
>[YouTube](https://www.youtube.com/) is an online video sharing and social media platform created by `Google`.
>[YouTube](https://www.youtube.com/) is an online video sharing and social media platform created by `Google`.
Use `YoutubeAudioLoader` to fetch / download the audio files.
@ -998,7 +997,7 @@ from langchain_community.document_loaders.parsers import OpenAIWhisperParser, Op
### YouTube transcripts
>[YouTube](https://www.youtube.com/) is an online video sharing and social media platform created by `Google`.
>[YouTube](https://www.youtube.com/) is an online video sharing and social media platform created by `Google`.
We need to install `youtube-transcript-api` python package.
To apply [weight-only quantization](https://github.com/huggingface/optimum-intel?tab=readme-ov-file#export) when exporting your model.
## Embedding Models
### Hugging Face Hub
>The [Hugging Face Hub](https://huggingface.co/docs/hub/index) is a platform
> with over 350k models, 75k datasets, and 150k demo apps (Spaces), all open source
> and publicly available, in an online platform where people can easily
> collaborate and build ML together. The Hub works as a central place where anyone
>The [Hugging Face Hub](https://huggingface.co/docs/hub/index) is a platform
> with over 350k models, 75k datasets, and 150k demo apps (Spaces), all open source
> and publicly available, in an online platform where people can easily
> collaborate and build ML together. The Hub works as a central place where anyone
> can explore, experiment, collaborate, and build technology with Machine Learning.
We need to install the `sentence_transformers` python package.
@ -71,7 +71,6 @@ We need to install the `sentence_transformers` python package.
pip install sentence_transformers
```
#### HuggingFaceEmbeddings
See a [usage example](/docs/integrations/text_embedding/huggingfacehub).
@ -79,6 +78,7 @@ See a [usage example](/docs/integrations/text_embedding/huggingfacehub).
```python
from langchain_community.embeddings import HuggingFaceEmbeddings
```
#### HuggingFaceInstructEmbeddings
See a [usage example](/docs/integrations/text_embedding/instruct_embeddings).
@ -89,8 +89,8 @@ from langchain_community.embeddings import HuggingFaceInstructEmbeddings
#### HuggingFaceBgeEmbeddings
>[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).
>BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.
>[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).
>BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.
See a [usage example](/docs/integrations/text_embedding/bge_huggingface).
@ -100,9 +100,9 @@ from langchain_community.embeddings import HuggingFaceBgeEmbeddings
### Hugging Face Text Embeddings Inference (TEI)
>[Hugging Face Text Embeddings Inference (TEI)](https://huggingface.co/docs/text-generation-inference/index) is a toolkit for deploying and serving open-source
>[Hugging Face Text Embeddings Inference (TEI)](https://huggingface.co/docs/text-generation-inference/index) is a toolkit for deploying and serving open-source
> text embeddings and sequence classification models. `TEI` enables high-performance extraction for the most popular models,
>including `FlagEmbedding`, `Ember`, `GTE` and `E5`.
>including `FlagEmbedding`, `Ember`, `GTE` and `E5`.
We need to install `huggingface-hub` python package.
@ -116,15 +116,14 @@ See a [usage example](/docs/integrations/text_embedding/text_embeddings_inferenc
from langchain_community.embeddings import HuggingFaceHubEmbeddings
```
## Document Loaders
### Hugging Face dataset
>[Hugging Face Hub](https://huggingface.co/docs/hub/index) is home to over 75,000
> [datasets](https://huggingface.co/docs/hub/index#datasets) in more than 100 languages
>[Hugging Face Hub](https://huggingface.co/docs/hub/index) is home to over 75,000
> [datasets](https://huggingface.co/docs/hub/index#datasets) in more than 100 languages
> that can be used for a broad range of tasks across NLP, Computer Vision, and Audio.
> They used for a diverse range of tasks such as translation, automatic speech
> They used for a diverse range of tasks such as translation, automatic speech
> recognition, and image classification.
We need to install `datasets` python package.
@ -139,13 +138,11 @@ See a [usage example](/docs/integrations/document_loaders/hugging_face_dataset).
from langchain_community.document_loaders.hugging_face_dataset import HuggingFaceDatasetLoader
```
## Tools
### Hugging Face Hub Tools
>[Hugging Face Tools](https://huggingface.co/docs/transformers/v4.29.0/en/custom_tools)
>[Hugging Face Tools](https://huggingface.co/docs/transformers/v4.29.0/en/custom_tools)
> support text I/O and are loaded using the `load_huggingface_tool` function.
@ -21,11 +21,12 @@ from langchain_openai import AzureOpenAI
```
## Chat Models
### Azure OpenAI
>[Microsoft Azure](https://en.wikipedia.org/wiki/Microsoft_Azure), often referred to as `Azure` is a cloud computing platform run by `Microsoft`, which offers access, management, and development of applications and services through global data centers. It provides a range of capabilities, including software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). `Microsoft Azure` supports many programming languages, tools, and frameworks, including Microsoft-specific and third-party software and systems.
>[Microsoft Azure](https://en.wikipedia.org/wiki/Microsoft_Azure), often referred to as `Azure` is a cloud computing platform run by `Microsoft`, which offers access, management, and development of applications and services through global data centers. It provides a range of capabilities, including software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). `Microsoft Azure` supports many programming languages, tools, and frameworks, including Microsoft-specific and third-party software and systems.
>[Azure OpenAI](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/) is an `Azure` service with powerful language models from `OpenAI` including the `GPT-3`, `Codex` and `Embeddings model` series for content generation, summarization, semantic search, and natural language to code translation.
>[Azure OpenAI](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/) is an `Azure` service with powerful language models from `OpenAI` including the `GPT-3`, `Codex` and `Embeddings model` series for content generation, summarization, semantic search, and natural language to code translation.
See a [usage example](/docs/integrations/chat/azure_chat_openai)
```python
from langchain_openai import AzureChatOpenAI
```
## Embedding Models
### Azure OpenAI
See a [usage example](/docs/integrations/text_embedding/azureopenai)
@ -60,12 +61,12 @@ from langchain_openai import AzureOpenAIEmbeddings
### Azure AI Data
>[Azure AI Studio](https://ai.azure.com/) provides the capability to upload data assets
>[Azure AI Studio](https://ai.azure.com/) provides the capability to upload data assets
> to cloud storage and register existing data assets from the following sources:
>
>- `Microsoft OneLake`
>- `Azure Blob Storage`
>- `Azure Data Lake gen 2`
>- `Microsoft OneLake`
>- `Azure Blob Storage`
>- `Azure Data Lake gen 2`
First, you need to install several python packages.
@ -79,15 +80,14 @@ See a [usage example](/docs/integrations/document_loaders/azure_ai_data).
from langchain.document_loaders import AzureAIDataLoader
```
### Azure AI Document Intelligence
>[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known
>[Azure AI Document Intelligence](https://aka.ms/doc-intelligence) (formerly known
> as `Azure Form Recognizer`) is machine-learning
> based service that extracts text (including handwriting), tables or key-value-pairs
> from scanned documents or images.
>
>Document Intelligence supports `PDF`, `JPEG`, `PNG`, `BMP`, or `TIFF`.
>Document Intelligence supports `PDF`, `JPEG`, `PNG`, `BMP`, or `TIFF`.
First, you need to install a python package.
@ -101,16 +101,16 @@ See a [usage example](/docs/integrations/document_loaders/azure_document_intelli
from langchain.document_loaders import AzureAIDocumentIntelligenceLoader
```
### Azure Blob Storage
>[Azure Blob Storage](https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-introduction) is Microsoft's object storage solution for the cloud. Blob Storage is optimized for storing massive amounts of unstructured data. Unstructured data is data that doesn't adhere to a particular data model or definition, such as text or binary data.
>[Azure Blob Storage](https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-introduction) is Microsoft's object storage solution for the cloud. Blob Storage is optimized for storing massive amounts of unstructured data. Unstructured data is data that doesn't adhere to a particular data model or definition, such as text or binary data.
> file shares in the cloud that are accessible via the industry standard Server Message Block (`SMB`) protocol,
> Network File System (`NFS`) protocol, and `Azure Files REST API`. `Azure Files` are based on the `Azure Blob Storage`.
`Azure Blob Storage` is designed for:
- Serving images or documents directly to a browser.
- Storing files for distributed access.
- Streaming video and audio.
@ -134,10 +134,9 @@ See a [usage example for the Azure Files](/docs/integrations/document_loaders/az
from langchain_community.document_loaders import AzureBlobStorageFileLoader
```
### Microsoft OneDrive
>[Microsoft OneDrive](https://en.wikipedia.org/wiki/OneDrive) (formerly `SkyDrive`) is a file-hosting service operated by Microsoft.
>[Microsoft OneDrive](https://en.wikipedia.org/wiki/OneDrive) (formerly `SkyDrive`) is a file-hosting service operated by Microsoft.
First, you need to install a python package.
@ -151,10 +150,9 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_onedrive).
from langchain_community.document_loaders import OneDriveLoader
```
### Microsoft Word
>[Microsoft Word](https://www.microsoft.com/en-us/microsoft-365/word) is a word processor developed by Microsoft.
>[Microsoft Word](https://www.microsoft.com/en-us/microsoft-365/word) is a word processor developed by Microsoft.
See a [usage example](/docs/integrations/document_loaders/microsoft_word).
@ -162,16 +160,15 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_word).
from langchain_community.document_loaders import UnstructuredWordDocumentLoader
```
### Microsoft Excel
>[Microsoft Excel](https://en.wikipedia.org/wiki/Microsoft_Excel) is a spreadsheet editor developed by
> Microsoft for Windows, macOS, Android, iOS and iPadOS.
> It features calculation or computation capabilities, graphing tools, pivot tables, and a macro programming
>[Microsoft Excel](https://en.wikipedia.org/wiki/Microsoft_Excel) is a spreadsheet editor developed by
> Microsoft for Windows, macOS, Android, iOS and iPadOS.
> It features calculation or computation capabilities, graphing tools, pivot tables, and a macro programming
> language called Visual Basic for Applications (VBA). Excel forms part of the Microsoft 365 suite of software.
The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files.
The page content will be the raw text of the Excel file. If you use the loader in `"elements"` mode, an HTML
The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files.
The page content will be the raw text of the Excel file. If you use the loader in `"elements"` mode, an HTML
representation of the Excel file will be available in the document metadata under the `text_as_html` key.
See a [usage example](/docs/integrations/document_loaders/microsoft_excel).
@ -180,11 +177,10 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_excel).
from langchain_community.document_loaders import UnstructuredExcelLoader
```
### Microsoft SharePoint
>[Microsoft SharePoint](https://en.wikipedia.org/wiki/SharePoint) is a website-based collaboration system
> that uses workflow applications, “list” databases, and other web parts and security features to
>[Microsoft SharePoint](https://en.wikipedia.org/wiki/SharePoint) is a website-based collaboration system
> that uses workflow applications, “list” databases, and other web parts and security features to
> empower business teams to work together developed by Microsoft.
See a [usage example](/docs/integrations/document_loaders/microsoft_sharepoint).
@ -193,10 +189,9 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_sharepoint).
from langchain_community.document_loaders.sharepoint import SharePointLoader
```
### Microsoft PowerPoint
>[Microsoft PowerPoint](https://en.wikipedia.org/wiki/Microsoft_PowerPoint) is a presentation program by Microsoft.
>[Microsoft PowerPoint](https://en.wikipedia.org/wiki/Microsoft_PowerPoint) is a presentation program by Microsoft.
See a [usage example](/docs/integrations/document_loaders/microsoft_powerpoint).
@ -222,7 +217,7 @@ from langchain_community.document_loaders.onenote import OneNoteLoader
### Azure Cosmos DB
>[Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/) makes it easy to create a database with full native MongoDB support.
>[Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/) makes it easy to create a database with full native MongoDB support.
> You can apply your MongoDB experience and continue to use your favorite MongoDB drivers, SDKs, and tools by pointing your application to the API for MongoDB vCore account's connection string.
> Use vector search in Azure Cosmos DB for MongoDB vCore to seamlessly integrate your AI-based applications with your data that's stored in Azure Cosmos DB.
@ -251,16 +246,18 @@ from langchain_community.vectorstores import AzureCosmosDBVectorSearch
```
## Retrievers
### Azure Cognitive Search
>[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.
>[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.
>Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:
>- A search engine for full text search over a search index containing user-owned content
>- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation
>- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more
>- Programmability through REST APIs and client libraries in Azure SDKs
>- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)
> Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:
>
> - A search engine for full text search over a search index containing user-owned content
> - Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation
> - Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more
> - Programmability through REST APIs and client libraries in Azure SDKs
> - Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)
See [set up instructions](https://learn.microsoft.com/en-us/azure/search/search-create-service-portal).
@ -285,6 +282,7 @@ See a [usage example](/docs/integrations/toolkits/azure_cognitive_services).
```python
from langchain_community.agent_toolkits import O365Toolkit
```
### Microsoft Office 365 email and calendar
We need to install `O365` python package.
@ -293,7 +291,6 @@ We need to install `O365` python package.
pip install O365
```
See a [usage example](/docs/integrations/toolkits/office365).
```python
@ -319,7 +316,7 @@ from langchain_community.utilities.powerbi import PowerBIDataset
### Bing Search API
>[Microsoft Bing](https://www.bing.com/), commonly referred to as `Bing` or `Bing Search`,
>[Microsoft Bing](https://www.bing.com/), commonly referred to as `Bing` or `Bing Search`,
> is a web search engine owned and operated by `Microsoft`.
See a [usage example](/docs/integrations/tools/bing_search).
@ -332,9 +329,9 @@ from langchain_community.utilities import BingSearchAPIWrapper
### Microsoft Presidio
>[Presidio](https://microsoft.github.io/presidio/) (Origin from Latin praesidium ‘protection, garrison’)
> helps to ensure sensitive data is properly managed and governed. It provides fast identification and
> anonymization modules for private entities in text and images such as credit card numbers, names,
>[Presidio](https://microsoft.github.io/presidio/) (Origin from Latin praesidium ‘protection, garrison’)
> helps to ensure sensitive data is properly managed and governed. It provides fast identification and
> anonymization modules for private entities in text and images such as credit card numbers, names,
> locations, social security numbers, bitcoin wallets, US phone numbers, financial data and more.
First, you need to install several python packages and download a `SpaCy` model.
@ -349,4 +346,3 @@ See [usage examples](/docs/guides/privacy/presidio_data_anonymization/).
```python
from langchain_experimental.data_anonymizer import PresidioAnonymizer, PresidioReversibleAnonymizer
>[Activeloop Deep Lake](https://docs.activeloop.ai/) is a data lake for Deep Learning applications, allowing you to use it
>[Activeloop Deep Lake](https://docs.activeloop.ai/) is a data lake for Deep Learning applications, allowing you to use it
> as a vector store.
## Why Deep Lake?
@ -12,7 +12,6 @@
`Activeloop Deep Lake` supports `SelfQuery Retrieval`:
[Activeloop Deep Lake Self Query Retrieval](/docs/integrations/retrievers/self_query/activeloop_deeplake_self_query)
## More Resources
1. [Ultimate Guide to LangChain & Deep Lake: Build ChatGPT to Answer Questions on Your Financial Data](https://www.activeloop.ai/resources/ultimate-guide-to-lang-chain-deep-lake-build-chat-gpt-to-answer-questions-on-your-financial-data/)
>[Airtable](https://en.wikipedia.org/wiki/Airtable) is a cloud collaboration service.
`Airtable` is a spreadsheet-database hybrid, with the features of a database but applied to a spreadsheet.
> The fields in an Airtable table are similar to cells in a spreadsheet, but have types such as 'checkbox',
>[Airtable](https://en.wikipedia.org/wiki/Airtable) is a cloud collaboration service.
> `Airtable` is a spreadsheet-database hybrid, with the features of a database but applied to a spreadsheet.
> The fields in an Airtable table are similar to cells in a spreadsheet, but have types such as 'checkbox',
> 'phone number', and 'drop-down list', and can reference file attachments like images.
>Users can create a database, set up column types, add records, link tables to one another, collaborate, sort records
>Users can create a database, set up column types, add records, link tables to one another, collaborate, sort records
> and publish views to external websites.
## Installation and Setup
@ -14,13 +14,12 @@
pip install pyairtable
```
* Get your [API key](https://support.airtable.com/docs/creating-and-using-api-keys-and-access-tokens).
* Get the [ID of your base](https://airtable.com/developers/web/api/introduction).
* Get the [table ID from the table url](https://www.highviewapps.com/kb/where-can-i-find-the-airtable-base-id-and-table-id/#:~:text=Both%20the%20Airtable%20Base%20ID,URL%20that%20begins%20with%20tbl).
- Get your [API key](https://support.airtable.com/docs/creating-and-using-api-keys-and-access-tokens).
- Get the [ID of your base](https://airtable.com/developers/web/api/introduction).
- Get the [table ID from the table url](https://www.highviewapps.com/kb/where-can-i-find-the-airtable-base-id-and-table-id/#:~:text=Both%20the%20Airtable%20Base%20ID,URL%20that%20begins%20with%20tbl).
## Document Loader
```python
from langchain_community.document_loaders import AirtableLoader
>[Aleph Alpha](https://docs.aleph-alpha.com/) was founded in 2019 with the mission to research and build the foundational technology for an era of strong AI. The team of international scientists, engineers, and innovators researches, develops, and deploys transformative AI like large language and multimodal models and runs the fastest European commercial AI cluster.
>[Aleph Alpha](https://docs.aleph-alpha.com/) was founded in 2019 with the mission to research and build the foundational technology for an era of strong AI. The team of international scientists, engineers, and innovators researches, develops, and deploys transformative AI like large language and multimodal models and runs the fastest European commercial AI cluster.
>[The Luminous series](https://docs.aleph-alpha.com/docs/introduction/luminous/) is a family of large language models.
>[The Luminous series](https://docs.aleph-alpha.com/docs/introduction/luminous/) is a family of large language models.
## Installation and Setup
@ -18,7 +18,6 @@ from getpass import getpass
ALEPH_ALPHA_API_KEY = getpass()
```
## LLM
See a [usage example](/docs/integrations/llms/aleph_alpha).
>[Anyscale](https://www.anyscale.com) is a platform to run, fine tune and scale LLMs via production-ready APIs.
>[Anyscale](https://www.anyscale.com) is a platform to run, fine tune and scale LLMs via production-ready APIs.
> [Anyscale Endpoints](https://docs.anyscale.com/endpoints/overview) serve many open-source models in a cost-effective way.
`Anyscale` also provides [an example](https://docs.anyscale.com/endpoints/model-serving/examples/langchain-integration)
`Anyscale` also provides [an example](https://docs.anyscale.com/endpoints/model-serving/examples/langchain-integration)
how to setup `LangChain` with `Anyscale` for advanced chat agents.
## Installation and Setup
- Get an Anyscale Service URL, route and API key and set them as environment variables (`ANYSCALE_SERVICE_URL`,`ANYSCALE_SERVICE_ROUTE`, `ANYSCALE_SERVICE_TOKEN`).
- Get an Anyscale Service URL, route and API key and set them as environment variables (`ANYSCALE_SERVICE_URL`,`ANYSCALE_SERVICE_ROUTE`, `ANYSCALE_SERVICE_TOKEN`).
- Please see [the Anyscale docs](https://www.anyscale.com/get-started) for more details.
>[ArangoDB](https://github.com/arangodb/arangodb) is a scalable graph database system to
>[ArangoDB](https://github.com/arangodb/arangodb) is a scalable graph database system to
> drive value from connected data, faster. Native graphs, an integrated search engine, and JSON support, via a single query language. ArangoDB runs on-prem, in the cloud – anywhere.
## Installation and Setup
@ -13,7 +13,7 @@ pip install python-arango
## Graph QA Chain
Connect your `ArangoDB` Database with a chat model to get insights on your data.
Connect your `ArangoDB` Database with a chat model to get insights on your data.
See the notebook example [here](/docs/use_cases/graph/integrations/graph_arangodb_qa).
>[Baseten](https://baseten.co) is a provider of all the infrastructure you need to deploy and serve
>[Baseten](https://baseten.co) is a provider of all the infrastructure you need to deploy and serve
> ML models performantly, scalably, and cost-efficiently.
>As a model inference platform, `Baseten` is a `Provider` in the LangChain ecosystem.
The `Baseten` integration currently implements a single `Component`, LLMs, but more are planned!
>As a model inference platform, `Baseten` is a `Provider` in the LangChain ecosystem.
> The `Baseten` integration currently implements a single `Component`, LLMs, but more are planned!
>`Baseten` lets you run both open source models like Llama 2 or Mistral and run proprietary or
fine-tuned models on dedicated GPUs. If you're used to a provider like OpenAI, using Baseten has a few differences:
>`Baseten` lets you run both open source models like Llama 2 or Mistral and run proprietary or
> fine-tuned models on dedicated GPUs. If you're used to a provider like OpenAI, using Baseten has a few differences:
>* Rather than paying per token, you pay per minute of GPU used.
>* Every model on Baseten uses [Truss](https://truss.baseten.co/welcome), our open-source model packaging framework, for maximum customizability.
>* While we have some [OpenAI ChatCompletions-compatible models](https://docs.baseten.co/api-reference/openai), you can define your own I/O spec with `Truss`.
> - Rather than paying per token, you pay per minute of GPU used.
> - Every model on Baseten uses [Truss](https://truss.baseten.co/welcome), our open-source model packaging framework, for maximum customizability.
> - While we have some [OpenAI ChatCompletions-compatible models](https://docs.baseten.co/api-reference/openai), you can define your own I/O spec with `Truss`.
>[Learn more](https://docs.baseten.co/deploy/lifecycle) about model IDs and deployments.
>[Learn more](https://docs.baseten.co/deploy/lifecycle) about model IDs and deployments.
>Learn more about Baseten in [the Baseten docs](https://docs.baseten.co/).
>Learn more about Baseten in [the Baseten docs](https://docs.baseten.co/).
> [Apache Cassandra®](https://cassandra.apache.org/) is a NoSQL, row-oriented, highly scalable and highly available database.
> Starting with version 5.0, the database ships with [vector search capabilities](https://cassandra.apache.org/doc/trunk/cassandra/vector-search/overview.html).
The integrations outlined in this page can be used with `Cassandra` as well as other CQL-compatible databases,
The integrations outlined in this page can be used with `Cassandra` as well as other CQL-compatible databases,
i.e. those using the `Cassandra Query Language` protocol.
## Installation and Setup
Install the following Python package:
@ -31,7 +30,6 @@ from langchain_community.chat_message_histories import CassandraChatMessageHisto
Learn more in the [example notebook](/docs/integrations/memory/cassandra_chat_message_history).
## LLM Cache
```python
@ -42,7 +40,6 @@ set_llm_cache(CassandraCache())
Learn more in the [example notebook](/docs/integrations/llms/llm_caching#cassandra-caches) (scroll to the Cassandra section).
## Semantic LLM Cache
```python
@ -66,5 +63,5 @@ Learn more in the [example notebook](/docs/integrations/document_loaders/cassand
#### Attribution statement
> Apache Cassandra, Cassandra and Apache are either registered trademarks or trademarks of
> Apache Cassandra, Cassandra and Apache are either registered trademarks or trademarks of
> the [Apache Software Foundation](http://www.apache.org/) in the United States and/or other countries.
>[Chaindesk](https://chaindesk.ai) is an [open-source](https://github.com/gmpetrov/databerry) document retrieval platform that helps to connect your personal data with Large Language Models.
> [Chaindesk](https://chaindesk.ai) is an [open-source](https://github.com/gmpetrov/databerry) document retrieval platform that helps to connect your personal data with Large Language Models.
## Installation and Setup
We need to sign up for Chaindesk, create a datastore, add some data and get your datastore api endpoint url.
We need to sign up for Chaindesk, create a datastore, add some data and get your datastore api endpoint url.
We need the [API Key](https://docs.chaindesk.ai/api-reference/authentication).
>[Clarifai](https://clarifai.com) is one of first deep learning platforms having been founded in 2013. Clarifai provides an AI platform with the full AI lifecycle for data exploration, data labeling, model training, evaluation and inference around images, video, text and audio data. In the LangChain ecosystem, as far as we're aware, Clarifai is the only provider that supports LLMs, embeddings and a vector store in one production scale platform, making it an excellent choice to operationalize your LangChain implementations.
>[Clarifai](https://clarifai.com) is one of first deep learning platforms having been founded in 2013. Clarifai provides an AI platform with the full AI lifecycle for data exploration, data labeling, model training, evaluation and inference around images, video, text and audio data. In the LangChain ecosystem, as far as we're aware, Clarifai is the only provider that supports LLMs, embeddings and a vector store in one production scale platform, making it an excellent choice to operationalize your LangChain implementations.
## Installation and Setup
- Install the Python SDK:
```bash
pip install clarifai
```
[Sign-up](https://clarifai.com/signup) for a Clarifai account, then get a personal access token to access the Clarifai API from your [security settings](https://clarifai.com/settings/security) and set it as an environment variable (`CLARIFAI_PAT`).
[Sign-up](https://clarifai.com/signup) for a Clarifai account, then get a personal access token to access the Clarifai API from your [security settings](https://clarifai.com/settings/security) and set it as an environment variable (`CLARIFAI_PAT`).
For more details, the docs on the Clarifai LLM wrapper provide a [detailed walkthrough](/docs/integrations/llms/clarifai).
### Text Embedding Models
To find the selection of text embeddings models in the Clarifai platform you can select the text to embedding model type [here](https://clarifai.com/explore/models?page=1&perPage=24&filterData=%5B%7B%22field%22%3A%22model_type_id%22%2C%22value%22%3A%5B%22text-embedder%22%5D%7D%5D).
There is a Clarifai Embedding model in LangChain, which you can access with:
```python
from langchain_community.embeddings import ClarifaiEmbeddings
> [CnosDB](https://github.com/cnosdb/cnosdb) is an open-source distributed time series database with high performance, high compression rate and high ease of use.
## Installation and Setup
@ -8,8 +9,11 @@ pip install cnos-connector
```
## Connecting to CnosDB
You can connect to CnosDB using the `SQLDatabase.from_cnosdb()` method.
|RAG Retriever|Connect to external data sources|[chat + rag](https://docs.cohere.com/reference/chat)|`from langchain.retrievers import CohereRagRetriever`|[cohere.ipynb](/docs/integrations/retrievers/cohere)|
|Text Embedding|Embed strings to vectors|[embed](https://docs.cohere.com/reference/embed)|`from langchain_community.embeddings import CohereEmbeddings`|[cohere.ipynb](/docs/integrations/text_embedding/cohere)|
|Rerank Retriever|Rank strings based on relevance|[rerank](https://docs.cohere.com/reference/rerank)|`from langchain.retrievers.document_compressors import CohereRerank`|[cohere.ipynb](/docs/integrations/retrievers/cohere-reranker)|
|RAG Retriever|Connect to external data sources|[chat + rag](https://docs.cohere.com/reference/chat)|`from langchain.retrievers import CohereRagRetriever`|[cohere.ipynb](/docs/integrations/retrievers/cohere)|
|Text Embedding|Embed strings to vectors|[embed](https://docs.cohere.com/reference/embed)|`from langchain_community.embeddings import CohereEmbeddings`|[cohere.ipynb](/docs/integrations/text_embedding/cohere)|
|Rerank Retriever|Rank strings based on relevance|[rerank](https://docs.cohere.com/reference/rerank)|`from langchain.retrievers.document_compressors import CohereRerank`|[cohere.ipynb](/docs/integrations/retrievers/cohere-reranker)|
>[Confluence](https://www.atlassian.com/software/confluence) is a wiki collaboration platform that saves and organizes all of the project-related material. `Confluence` is a knowledge base that primarily handles content management activities.
> [Confluence](https://www.atlassian.com/software/confluence) is a wiki collaboration platform that saves and organizes all of the project-related material. `Confluence` is a knowledge base that primarily handles content management activities.
## Installation and Setup
@ -9,10 +8,9 @@
pip install atlassian-python-api
```
We need to set up `username/api_key` or `Oauth2 login`.
We need to set up `username/api_key` or `Oauth2 login`.
See [instructions](https://support.atlassian.com/atlassian-account/docs/manage-api-tokens-for-your-atlassian-account/).
## Document Loader
See a [usage example](/docs/integrations/document_loaders/confluence).
> [DashVector](https://help.aliyun.com/document_detail/2510225.html) is a fully-managed vectorDB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.
> [DashVector](https://help.aliyun.com/document_detail/2510225.html) is a fully-managed vectorDB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.
This document demonstrates to leverage DashVector within the LangChain ecosystem. In particular, it shows how to install DashVector, and how to use it as a VectorStore plugin in LangChain.
It is broken into two parts: installation and setup, and then references to specific DashVector wrappers.
## Installation and Setup
Install the Python SDK:
```bash
pip install dashvector
```
## VectorStore
A DashVector Collection is wrapped as a familiar VectorStore for native usage within LangChain,
A DashVector Collection is wrapped as a familiar VectorStore for native usage within LangChain,
which allows it to be readily used for various scenarios, such as semantic search or example selection.
You may import the vectorstore by:
```python
from langchain_community.vectorstores import DashVector
The [Databricks](https://www.databricks.com/) Lakehouse Platform unifies data, analytics, and AI on one platform.
@ -10,13 +9,11 @@ Databricks embraces the LangChain ecosystem in various ways:
3. Databricks as an LLM provider: Deploy your fine-tuned LLMs on Databricks via serving endpoints or cluster driver proxy apps, and query it as langchain.llms.Databricks
4. Databricks Dolly: Databricks open-sourced Dolly which allows for commercial use, and can be accessed through the Hugging Face Hub
Databricks connector for the SQLDatabase Chain
----------------------------------------------
You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.
## Databricks connector for the SQLDatabase Chain
You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.
Databricks MLflow integrates with LangChain
-------------------------------------------
## Databricks MLflow integrates with LangChain
MLflow is an open-source platform to manage the ML lifecycle, including experimentation, reproducibility, deployment, and a central model registry. See the notebook [MLflow Callback Handler](/docs/integrations/providers/mlflow_tracking) for details about MLflow's integration with LangChain.
@ -24,8 +21,7 @@ Databricks provides a fully managed and hosted version of MLflow integrated with
Databricks MLflow makes it more convenient to develop LangChain applications on Databricks. For MLflow tracking, you don't need to set the tracking uri. For MLflow Model Serving, you can save LangChain Chains in the MLflow langchain flavor, and then register and serve the Chain with a few clicks on Databricks, with credentials securely managed by MLflow Model Serving.
Databricks External Models
--------------------------
## Databricks External Models
[Databricks External Models](https://docs.databricks.com/generative-ai/external-models/index.html) is a service that is designed to streamline the usage and management of various large language model (LLM) providers, such as OpenAI and Anthropic, within an organization. It offers a high-level interface that simplifies the interaction with these services by providing a unified endpoint to handle specific LLM related requests. The following example creates an endpoint that serves OpenAI's GPT-4 model and generates a chat response from it:
[Databricks Foundation Model APIs](https://docs.databricks.com/machine-learning/foundation-models/index.html) allow you to access and query state-of-the-art open source models from dedicated serving endpoints. With Foundation Model APIs, developers can quickly and easily build applications that leverage a high-quality generative AI model without maintaining their own model deployment. The following example uses the `databricks-bge-large-en` endpoint to generate embeddings from text:
[Databricks Foundation Model APIs](https://docs.databricks.com/machine-learning/foundation-models/index.html) allow you to access and query state-of-the-art open source models from dedicated serving endpoints. With Foundation Model APIs, developers can quickly and easily build applications that leverage a high-quality generative AI model without maintaining their own model deployment. The following example uses the `databricks-bge-large-en` endpoint to generate embeddings from text:
```python
from langchain_community.embeddings import DatabricksEmbeddings
The notebook [Wrap Databricks endpoints as LLMs](/docs/integrations/llms/databricks#wrapping-a-serving-endpoint-custom-model) demonstrates how to serve a custom model that has been registered by MLflow as a Databricks endpoint.
It supports two types of endpoints: the serving endpoint, which is recommended for both production and development, and the cluster driver proxy app, which is recommended for interactive development.
It supports two types of endpoints: the serving endpoint, which is recommended for both production and development, and the cluster driver proxy app, which is recommended for interactive development.
Databricks Vector Search
------------------------
## Databricks Vector Search
Databricks Vector Search is a serverless similarity search engine that allows you to store a vector representation of your data, including metadata, in a vector database. With Vector Search, you can create auto-updating vector search indexes from Delta tables managed by Unity Catalog and query them with a simple API to return the most similar vectors. See the notebook [Databricks Vector Search](/docs/integrations/vectorstores/databricks_vector_search) for instructions to use it with LangChain.
>[ddtrace](https://github.com/DataDog/dd-trace-py) is a Datadog application performance monitoring (APM) library which provides an integration to monitor your LangChain application.
>[ddtrace](https://github.com/DataDog/dd-trace-py) is a Datadog application performance monitoring (APM) library which provides an integration to monitor your LangChain application.
Key features of the ddtrace integration for LangChain:
- Traces: Capture LangChain requests, parameters, prompt-completions, and help visualize LangChain operations.
- Metrics: Capture LangChain request latency, errors, and token/cost usage (for OpenAI LLMs and chat models).
- Logs: Store prompt completion data for each LangChain operation.
@ -35,7 +36,6 @@ docker run -d --cgroupns host \
pip install ddtrace>=1.17
```
3. The LangChain integration can be enabled automatically when you prefix your LangChain Python application command with `ddtrace-run`:
```
@ -68,12 +68,10 @@ patch(langchain=True)
See the [APM Python library documentation][https://ddtrace.readthedocs.io/en/stable/installation_quickstart.html] for more advanced usage.
## Configuration
See the [APM Python library documentation][https://ddtrace.readthedocs.io/en/stable/integrations.html#langchain] for all the available configuration options.
### Log Prompt & Completion Sampling
To enable log prompt and completion sampling, set the `DD_LANGCHAIN_LOGS_ENABLED=1` environment variable. By default, 10% of traced requests will emit logs containing the prompts and completions.
@ -82,7 +80,6 @@ To adjust the log sample rate, see the [APM library documentation][https://ddtra
**Note**: Logs submission requires `DD_API_KEY` to be specified when running `ddtrace-run`.
## Troubleshooting
Need help? Create an issue on [ddtrace](https://github.com/DataDog/dd-trace-py) or contact [Datadog support][https://docs.datadoghq.com/help/].
@ -8,7 +8,6 @@ It is broken into two parts: installation and setup, and then examples of DeepSp
- Install the Python package with `pip install deepsparse`
- Choose a [SparseZoo model](https://sparsezoo.neuralmagic.com/?useCase=text_generation) or export a support model to ONNX [using Optimum](https://github.com/neuralmagic/notebooks/blob/main/notebooks/opt-text-generation-deepsparse-quickstart/OPT_Text_Generation_DeepSparse_Quickstart.ipynb)
## LLMs
There exists a DeepSparse LLM wrapper, which you can access with:
>[Diffbot](https://docs.diffbot.com/docs) is a service to read web pages. Unlike traditional web scraping tools,
>[Diffbot](https://docs.diffbot.com/docs) is a service to read web pages. Unlike traditional web scraping tools,
> `Diffbot` doesn't require any rules to read the content on a page.
>It starts with computer vision, which classifies a page into one of 20 possible types. Content is then interpreted by a machine learning model trained to identify the key attributes on a page based on its type.
>The result is a website transformed into clean-structured data (like JSON or CSV), ready for your application.
>It starts with computer vision, which classifies a page into one of 20 possible types. Content is then interpreted by a machine learning model trained to identify the key attributes on a page based on its type.
>The result is a website transformed into clean-structured data (like JSON or CSV), ready for your application.
bracesproul
2 months ago