langchain/docs/docs/concepts.mdx

# Conceptual guide

import ThemedImage from '@theme/ThemedImage';
import useBaseUrl from '@docusaurus/useBaseUrl';

This section contains introductions to key parts of LangChain.

## Architecture

LangChain as a framework consists of several pieces. The below diagram shows how they relate.

<ThemedImage
  alt="Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers."
  sources={{
    light: useBaseUrl('/svg/langchain_stack.svg'),
    dark: useBaseUrl('/svg/langchain_stack_dark.svg'),
  }}
  title="LangChain Framework Overview"
/>

### `langchain-core`
This package contains base abstractions of different components and ways to compose them together.
The interfaces for core components like LLMs, vectorstores, retrievers and more are defined here.
No third party integrations are defined here.
The dependencies are kept purposefully very lightweight.

### `langchain-community`

This package contains third party integrations that are maintained by the LangChain community.
Key partner packages are separated out (see below).
This contains all integrations for various components (LLMs, vectorstores, retrievers).
All dependencies in this package are optional to keep the package as lightweight as possible.

### Partner packages

While the long tail of integrations are in `langchain-community`, we split popular integrations into their own packages (e.g. `langchain-openai`, `langchain-anthropic`, etc).
This was done in order to improve support for these important integrations.

### `langchain`

The main `langchain` package contains chains, agents, and retrieval strategies that make up an application's cognitive architecture.
These are NOT third party integrations.
All chains, agents, and retrieval strategies here are NOT specific to any one integration, but rather generic across all integrations.

### [LangGraph](/docs/langgraph)

Not currently in this repo, `langgraph` is an extension of `langchain` aimed at
building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.

LangGraph exposes high level interfaces for creating common types of agents, as well as a low-level API for constructing more contr

### [langserve](/docs/langserve)

A package to deploy LangChain chains as REST APIs. Makes it easy to get a production ready API up and running.

### [LangSmith](/docs/langsmith)

A developer platform that lets you debug, test, evaluate, and monitor LLM applications.

## Installation

If you want to work with high level abstractions, you should install the `langchain` package.

```shell
pip install langchain
```

If you want to work with specific integrations, you will need to install them separately.
See [here](/docs/integrations/platforms/) for a list of integrations and how to install them.

For working with LangSmith, you will need to set up a LangSmith developer account [here](https://smith.langchain.com) and get an API key.
After that, you can enable it by setting environment variables:

```shell
export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=ls__...
```

## LangChain Expression Language

LangChain Expression Language, or LCEL, is a declarative way to easily compose chains together.
LCEL was designed from day 1 to **support putting prototypes in production, with no code changes**, from the simplest “prompt + LLM” chain to the most complex chains (we’ve seen folks successfully run LCEL chains with 100s of steps in production). To highlight a few of the reasons you might want to use LCEL:

**First-class streaming support**
When you build your chains with LCEL you get the best possible time-to-first-token (time elapsed until the first chunk of output comes out). For some chains this means eg. we stream tokens straight from an LLM to a streaming output parser, and you get back parsed, incremental chunks of output at the same rate as the LLM provider outputs the raw tokens.

**Async support**
Any chain built with LCEL can be called both with the synchronous API (eg. in your Jupyter notebook while prototyping) as well as with the asynchronous API (eg. in a [LangServe](/docs/langsmith) server). This enables using the same code for prototypes and in production, with great performance, and the ability to handle many concurrent requests in the same server.

**Optimized parallel execution**
Whenever your LCEL chains have steps that can be executed in parallel (eg if you fetch documents from multiple retrievers) we automatically do it, both in the sync and the async interfaces, for the smallest possible latency.

**Retries and fallbacks**
Configure retries and fallbacks for any part of your LCEL chain. This is a great way to make your chains more reliable at scale. We’re currently working on adding streaming support for retries/fallbacks, so you can get the added reliability without any latency cost.

**Access intermediate results**
For more complex chains it’s often very useful to access the results of intermediate steps even before the final output is produced. This can be used to let end-users know something is happening, or even just to debug your chain. You can stream intermediate results, and it’s available on every [LangServe](/docs/langserve) server.

**Input and output schemas**
Input and output schemas give every LCEL chain Pydantic and JSONSchema schemas inferred from the structure of your chain. This can be used for validation of inputs and outputs, and is an integral part of LangServe.

[**Seamless LangSmith tracing**](/docs/langsmith)
As your chains get more and more complex, it becomes increasingly important to understand what exactly is happening at every step.
With LCEL, **all** steps are automatically logged to [LangSmith](/docs/langsmith/) for maximum observability and debuggability.

[**Seamless LangServe deployment**](/docs/langserve)
Any chain created with LCEL can be easily deployed using [LangServe](/docs/langserve).

### Interface

To make it as easy as possible to create custom chains, we've implemented a ["Runnable"](https://api.python.langchain.com/en/stable/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable) protocol. Many LangChain components implement the `Runnable` protocol, including chat models, LLMs, output parsers, retrievers, prompt templates, and more. There are also several useful primitives for working with runnables, which you can read about below.

This is a standard interface, which makes it easy to define custom chains as well as invoke them in a standard way.
The standard interface includes:

- [`stream`](#stream): stream back chunks of the response
- [`invoke`](#invoke): call the chain on an input
- [`batch`](#batch): call the chain on a list of inputs

These also have corresponding async methods that should be used with [asyncio](https://docs.python.org/3/library/asyncio.html) `await` syntax for concurrency:

- `astream`: stream back chunks of the response async
- `ainvoke`: call the chain on an input async
- `abatch`: call the chain on a list of inputs async
- `astream_log`: stream back intermediate steps as they happen, in addition to the final response
- `astream_events`: **beta** stream events as they happen in the chain (introduced in `langchain-core` 0.1.14)

The **input type** and **output type** varies by component:

| Component | Input Type | Output Type |
| --- | --- | --- |
| Prompt | Dictionary | PromptValue |
| ChatModel | Single string, list of chat messages or a PromptValue | ChatMessage |
| LLM | Single string, list of chat messages or a PromptValue | String |
| OutputParser | The output of an LLM or ChatModel | Depends on the parser |
| Retriever | Single string | List of Documents |
| Tool | Single string or dictionary, depending on the tool | Depends on the tool |


All runnables expose input and output **schemas** to inspect the inputs and outputs:
- `input_schema`: an input Pydantic model auto-generated from the structure of the Runnable
- `output_schema`: an output Pydantic model auto-generated from the structure of the Runnable

## Components

LangChain provides standard, extendable interfaces and external integrations for various components useful for building with LLMs.
Some components LangChain implements, some components we rely on third-party integrations for, and others are a mix.

### LLMs
Language models that takes a string as input and returns a string.
These are traditionally older models (newer models generally are `ChatModels`, see below).

Although the underlying models are string in, string out, the LangChain wrappers also allow these models to take messages as input.
This makes them interchangeable with ChatModels.
When messages are passed in as input, they will be formatted into a string under the hood before being passed to the underlying model.

LangChain does not provide any LLMs, rather we rely on third party integrations.

### Chat models
Language models that use a sequence of messages as inputs and return chat messages as outputs (as opposed to using plain text).
These are traditionally newer models (older models are generally `LLMs`, see above).
Chat models support the assignment of distinct roles to conversation messages, helping to distinguish messages from the AI, users, and instructions such as system messages.

Although the underlying models are messages in, message out, the LangChain wrappers also allow these models to take a string as input.
This makes them interchangeable with LLMs (and simpler to use).
When a string is passed in as input, it will be converted to a HumanMessage under the hood before being passed to the underlying model.

LangChain does not provide any ChatModels, rather we rely on third party integrations.

We have some standardized parameters when constructing ChatModels:
- `model`: the name of the model

ChatModels also accept other parameters that are specific to that integration.

### Function/Tool Calling

:::info
We use the term tool calling interchangeably with function calling. Although
function calling is sometimes meant to refer to invocations of a single function,
we treat all models as though they can return multiple tool or function calls in
each message.
:::

Tool calling allows a model to respond to a given prompt by generating output that
matches a user-defined schema. While the name implies that the model is performing
some action, this is actually not the case! The model is coming up with the
arguments to a tool, and actually running the tool (or not) is up to the user -
for example, if you want to [extract output matching some schema](/docs/tutorial/extraction/)
from unstructured text, you could give the model an "extraction" tool that takes
parameters matching the desired schema, then treat the generated output as your final
result.

A tool call includes a name, arguments dict, and an optional identifier. The
arguments dict is structured `{argument_name: argument_value}`.

Many LLM providers, including [Anthropic](https://www.anthropic.com/),
[Cohere](https://cohere.com/), [Google](https://cloud.google.com/vertex-ai),
[Mistral](https://mistral.ai/), [OpenAI](https://openai.com/), and others,
support variants of a tool calling feature. These features typically allow requests
to the LLM to include available tools and their schemas, and for responses to include
calls to these tools. For instance, given a search engine tool, an LLM might handle a
query by first issuing a call to the search engine. The system calling the LLM can
receive the tool call, execute it, and return the output to the LLM to inform its
response. LangChain includes a suite of [built-in tools](/docs/integrations/tools/)
and supports several methods for defining your own [custom tools](/docs/how_to/custom_tools).

There are two main use cases for function/tool calling:

- [How to return structured data from an LLM](/docs/how_to/structured_output/)
- [How to use a model to call tools](/docs/how_to/tool_calling/)


### Message types

Some language models take a list of messages as input and return a message.
There are a few different types of messages.
All messages have a `role`, `content`, and `response_metadata` property.

The `role` describes WHO is saying the message.
LangChain has different message classes for different roles.

The `content` property describes the content of the message.
This can be a few different things:

- A string (most models deal this type of content)
- A List of dictionaries (this is used for multi-modal input, where the dictionary contains information about that input type and that input location)

#### HumanMessage

This represents a message from the user.

#### AIMessage

This represents a message from the model. In addition to the `content` property, these messages also have:

**`response_metadata`**

The `response_metadata` property contains additional metadata about the response. The data here is often specific to each model provider.
This is where information like log-probs and token usage may be stored.

**`tool_calls`**

These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.
They can be accessed from there with the `.tool_calls` property.

This property returns a list of dictionaries. Each dictionary has the following keys:

- `name`: The name of the tool that should be called.
- `args`: The arguments to that tool.
- `id`: The id of that tool call.

#### SystemMessage

This represents a system message, which tells the model how to behave. Not every model provider supports this.

#### FunctionMessage

This represents the result of a function call. In addition to `role` and `content`, this message has a `name` parameter which conveys the name of the function that was called to produce this result.

#### ToolMessage

This represents the result of a tool call. This is distinct from a FunctionMessage in order to match OpenAI's `function` and `tool` message types. In addition to `role` and `content`, this message has a `tool_call_id` parameter which conveys the id of the call to the tool that was called to produce this result.


### Prompt templates
Prompt templates help to translate user input and parameters into instructions for a language model.
This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.

Prompt Templates take as input a dictionary, where each key represents a variable in the prompt template to fill in.

Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages.
The reason this PromptValue exists is to make it easy to switch between strings and messages.

There are a few different types of prompt templates

#### String PromptTemplates

These prompt templates are used to format a single string, and generally are used for simpler inputs.
For example, a common way to construct and use a PromptTemplate is as follows:

```python
from langchain_core.prompts import PromptTemplate

prompt_template = PromptTemplate.from_template("Tell me a joke about {topic}")

prompt_template.invoke({"topic": "cats"})
```

#### ChatPromptTemplates

These prompt templates are used to format a list of messages. These "templates" consist of a list of templates themselves.
For example, a common way to construct and use a ChatPromptTemplate is as follows:

```python
from langchain_core.prompts import ChatPromptTemplate

prompt_template = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant"),
    ("user", "Tell me a joke about {topic}"
])

prompt_template.invoke({"topic": "cats"})
```

In the above example, this ChatPromptTemplate will construct two messages when called.
The first is a system message, that has no variables to format.
The second is a HumanMessage, and will be formatted by the `topic` variable the user passes in.

#### MessagesPlaceholder

This prompt template is responsible for adding a list of messages in a particular place.
In the above ChatPromptTemplate, we saw how we could format two messages, each one a string.
But what if we wanted the user to pass in a list of messages that we would slot into a particular spot?
This is how you use MessagesPlaceholder.

```python
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.messages import HumanMessage

prompt_template = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant"),
    MessagesPlaceholder("msgs")
])

prompt_template.invoke({"msgs": [HumanMessage(content="hi!")]})
```

This will produce a list of two messages, the first one being a system message, and the second one being the HumanMessage we passed in.
If we had passed in 5 messages, then it would have produced 6 messages in total (the system message plus the 5 passed in).
This is useful for letting a list of messages be slotted into a particular spot.

An alternative way to accomplish the same thing without using the `MessagesPlaceholder` class explicitly is:

```python
prompt_template = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant"),
    ("placeholder", "{msgs}") # <-- This is the changed part
])
```

### Example Selectors
One common prompting technique for achieving better performance is to include examples as part of the prompt.
This gives the language model concrete examples of how it should behave.
Sometimes these examples are hardcoded into the prompt, but for more advanced situations it may be nice to dynamically select them.
Example Selectors are classes responsible for selecting and then formatting examples into prompts.


### Output parsers

:::note

The information here refers to parsers that take a text output from a model try to parse it into a more structured representation.
More and more models are supporting function (or tool) calling, which handles this automatically.
It is recommended to use function/tool calling rather than output parsing.
See documentation for that [here](/docs/concepts/#function-tool-calling).

:::

Responsible for taking the output of a model and transforming it to a more suitable format for downstream tasks.
Useful when you are using LLMs to generate structured data, or to normalize output from chat models and LLMs.

LangChain has lots of different types of output parsers. This is a list of output parsers LangChain supports. The table below has various pieces of information:

**Name**: The name of the output parser

**Supports Streaming**: Whether the output parser supports streaming.

**Has Format Instructions**: Whether the output parser has format instructions. This is generally available except when (a) the desired schema is not specified in the prompt but rather in other parameters (like OpenAI function calling), or (b) when the OutputParser wraps another OutputParser.

**Calls LLM**: Whether this output parser itself calls an LLM. This is usually only done by output parsers that attempt to correct misformatted output.

**Input Type**: Expected input type. Most output parsers work on both strings and messages, but some (like OpenAI Functions) need a message with specific kwargs.

**Output Type**: The output type of the object returned by the parser.

**Description**: Our commentary on this output parser and when to use it.

| Name            | Supports Streaming | Has Format Instructions       | Calls LLM | Input Type                       | Output Type          | Description                                                                                                                                                                                                                                              |
|-----------------|--------------------|-------------------------------|-----------|----------------------------------|----------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [JSON](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.json.JsonOutputParser.html#langchain_core.output_parsers.json.JsonOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`               | JSON object          | Returns a JSON object as specified. You can specify a Pydantic model and it will return JSON for that model. Probably the most reliable output parser for getting structured data that does NOT use function calling.                                    |
| [XML](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.xml.XMLOutputParser.html#langchain_core.output_parsers.xml.XMLOutputParser)            | ✅                  | ✅                             |           | `str` \| `Message`                 | `dict`               | Returns a dictionary of tags. Use when XML output is needed. Use with models that are good at writing XML (like Anthropic's).                                                                                                                            |
| [CSV](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.list.CommaSeparatedListOutputParser.html#langchain_core.output_parsers.list.CommaSeparatedListOutputParser)           | ✅                  | ✅                             |           | `str` \| `Message`                 | `List[str]`          | Returns a list of comma separated values.                                                                                                                                                                                                                |
| [OutputFixing](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.fix.OutputFixingParser.html#langchain.output_parsers.fix.OutputFixingParser)    |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the error message and the bad output to an LLM and ask it to fix the output.                                                                                              |
| [RetryWithError](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.retry.RetryWithErrorOutputParser.html#langchain.output_parsers.retry.RetryWithErrorOutputParser)  |                    |                               | ✅         | `str` \| `Message`                 |                      | Wraps another output parser. If that output parser errors, then this will pass the original inputs, the bad output, and the error message to an LLM and ask it to fix it. Compared to OutputFixingParser, this one also sends the original instructions. |
| [Pydantic](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.pydantic.PydanticOutputParser.html#langchain_core.output_parsers.pydantic.PydanticOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format.                                                                                                                                                                                     |
| [YAML](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.yaml.YamlOutputParser.html#langchain.output_parsers.yaml.YamlOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `pydantic.BaseModel` | Takes a user defined Pydantic model and returns data in that format. Uses YAML to encode it.                                                                                                                                                                                    |
| [PandasDataFrame](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser.html#langchain.output_parsers.pandas_dataframe.PandasDataFrameOutputParser) |                    | ✅                             |           | `str` \| `Message`                 | `dict`               | Useful for doing operations with pandas DataFrames.                                                                                                                                                                                                      |
| [Enum](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.enum.EnumOutputParser.html#langchain.output_parsers.enum.EnumOutputParser)            |                    | ✅                             |           | `str` \| `Message`                 | `Enum`               | Parses response into one of the provided enum values.                                                                                                                                                                                                    |
| [Datetime](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.datetime.DatetimeOutputParser.html#langchain.output_parsers.datetime.DatetimeOutputParser)        |                    | ✅                             |           | `str` \| `Message`                 | `datetime.datetime`  | Parses response into a datetime string.                                                                                                                                                                                                                  |
| [Structured](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.structured.StructuredOutputParser.html#langchain.output_parsers.structured.StructuredOutputParser)      |                    | ✅                             |           | `str` \| `Message`                 | `Dict[str, str]`     | An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs.                                            |

### Chat History
Most LLM applications have a conversational interface.
An essential component of a conversation is being able to refer to information introduced earlier in the conversation.
At bare minimum, a conversational system should be able to access some window of past messages directly.

The concept of `ChatHistory` refers to a class in LangChain which can be used to wrap an arbitrary chain.
This `ChatHistory` will keep track of inputs and outputs of the underlying chain, and append them as messages to a message database
Future interactions will then load those messages and pass them into the chain as part of the input.

### Document

A Document object in LangChain contains information about some data. It has two attributes:

- `page_content: str`: The content of this document. Currently is only a string.
- `metadata: dict`: Arbitrary metadata associated with this document. Can track the document id, file name, etc.

### Document loaders

These classes load Document objects. LangChain has hundreds of integrations with various data sources to load data from: Slack, Notion, Google Drive, etc.

Each DocumentLoader has its own specific parameters, but they can all be invoked in the same way with the `.load` method.
An example use case is as follows:

```python
from langchain_community.document_loaders.csv_loader import CSVLoader

loader = CSVLoader(
    ...  # <-- Integration specific parameters here
)
data = loader.load()
```

### Text splitters

Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.

When you want to deal with long pieces of text, it is necessary to split up that text into chunks. As simple as this sounds, there is a lot of potential complexity here. Ideally, you want to keep the semantically related pieces of text together. What "semantically related" means could depend on the type of text. This notebook showcases several ways to do that.

At a high level, text splitters work as following:

1. Split the text up into small, semantically meaningful chunks (often sentences).
2. Start combining these small chunks into a larger chunk until you reach a certain size (as measured by some function).
3. Once you reach that size, make that chunk its own piece of text and then start creating a new chunk of text with some overlap (to keep context between chunks).

That means there are two different axes along which you can customize your text splitter:

1. How the text is split
2. How the chunk size is measured

### Embedding models
The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.

Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.

The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).

### Vectorstores
One of the most common ways to store and search over unstructured data is to embed it and store the resulting embedding vectors,
and then at query time to embed the unstructured query and retrieve the embedding vectors that are 'most similar' to the embedded query.
A vector store takes care of storing embedded data and performing vector search for you.

Vectorstores can be converted to the retriever interface by doing:

```python
vectorstore = MyVectorStore()
retriever = vectorstore.as_retriever()
```

### Retrievers
A retriever is an interface that returns documents given an unstructured query.
It is more general than a vector store.
A retriever does not need to be able to store documents, only to return (or retrieve) them.
Retrievers can be created from vectorstores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).

Retrievers accept a string query as input and return a list of Document's as output.

### Advanced Retrieval Types

LangChain provides several advanced retrieval types. A full list is below, along with the following information:

**Name**: Name of the retrieval algorithm.

**Index Type**: Which index type (if any) this relies on.

**Uses an LLM**: Whether this retrieval method uses an LLM.

**When to Use**: Our commentary on when you should considering using this retrieval method.

**Description**: Description of what this retrieval algorithm is doing.

| Name                      | Index Type                   | Uses an LLM               | When to Use                                                                                                                                   | Description                                                                                                                                                                                                                                                                                      |
|---------------------------|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Vectorstore](https://api.python.langchain.com/en/latest/vectorstores/langchain_core.vectorstores.VectorStoreRetriever.html#langchain_core.vectorstores.VectorStoreRetriever)               | Vectorstore                  | No                        | If you are just getting started and looking for something quick and easy.                                                                     | This is the simplest method and the one that is easiest to get started with. It involves creating embeddings for each piece of text.                                                                                                                                                             |
| [ParentDocument](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.parent_document_retriever.ParentDocumentRetriever.html#langchain.retrievers.parent_document_retriever.ParentDocumentRetriever)            | Vectorstore + Document Store | No                        | If your pages have lots of smaller pieces of distinct information that are best indexed by themselves, but best retrieved all together.       | This involves indexing multiple chunks for each document. Then you find the chunks that are most similar in embedding space, but you retrieve the whole parent document and return that (rather than individual chunks).                                                                         |
| [Multi Vector](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.multi_vector.MultiVectorRetriever.html#langchain.retrievers.multi_vector.MultiVectorRetriever)              | Vectorstore + Document Store | Sometimes during indexing | If you are able to extract information from documents that you think is more relevant to index than the text itself.                          | This involves creating multiple vectors for each document. Each vector could be created in a myriad of ways - examples include summaries of the text and hypothetical questions.                                                                                                                 |
| [Self Query](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.self_query.base.SelfQueryRetriever.html#langchain.retrievers.self_query.base.SelfQueryRetriever)               | Vectorstore                  | Yes                       | If users are asking questions that are better answered by fetching documents based on metadata rather than similarity with the text.          | This uses an LLM to transform user input into two things: (1) a string to look up semantically, (2) a metadata filer to go along with it. This is useful because oftentimes questions are about the METADATA of documents (not the content itself).                                              |
| [Contextual Compression](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.contextual_compression.ContextualCompressionRetriever.html#langchain.retrievers.contextual_compression.ContextualCompressionRetriever)    | Any                          | Sometimes                 | If you are finding that your retrieved documents contain too much irrelevant information and are distracting the LLM.                         | This puts a post-processing step on top of another retriever and extracts only the most relevant information from retrieved documents. This can be done with embeddings or an LLM.                                                                                                               |
| [Time-Weighted Vectorstore](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.time_weighted_retriever.TimeWeightedVectorStoreRetriever.html#langchain.retrievers.time_weighted_retriever.TimeWeightedVectorStoreRetriever) | Vectorstore                  | No                        | If you have timestamps associated with your documents, and you want to retrieve the most recent ones                                          | This fetches documents based on a combination of semantic similarity (as in normal vector retrieval) and recency (looking at timestamps of indexed documents)                                                                                                                                    |
| [Multi-Query Retriever](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.multi_query.MultiQueryRetriever.html#langchain.retrievers.multi_query.MultiQueryRetriever)     | Any                          | Yes                       | If users are asking questions that are complex and require multiple pieces of distinct information to respond                                 | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them.                             |
| [Ensemble](https://api.python.langchain.com/en/latest/retrievers/langchain.retrievers.ensemble.EnsembleRetriever.html#langchain.retrievers.ensemble.EnsembleRetriever)                  | Any                          | No                        | If you have multiple retrieval methods and want to try combining them.                                                                        | This fetches documents from multiple retrievers and then combines them.                                                                                                                                                                                                                          |

### Tools
Tools are interfaces that an agent, chain, or LLM can use to interact with the world.
They combine a few things:

1. The name of the tool
2. A description of what the tool is
3. JSON schema of what the inputs to the tool are
4. The function to call
5. Whether the result of a tool should be returned directly to the user

It is useful to have all this information because this information can be used to build action-taking systems! The name, description, and JSON schema can be used to prompt the LLM so it knows how to specify what action to take, and then the function to call is equivalent to taking that action.

The simpler the input to a tool is, the easier it is for an LLM to be able to use it.
Many agents will only work with tools that have a single string input.

Importantly, the name, description, and JSON schema (if used) are all used in the prompt. Therefore, it is really important that they are clear and describe exactly how the tool should be used. You may need to change the default name, description, or JSON schema if the LLM is not understanding how to use the tool.


### Toolkits

Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.

All Toolkits expose a `get_tools` method which returns a list of tools.
You can therefore do:

```python
# Initialize a toolkit
toolkit = ExampleTookit(...)

# Get list of tools
tools = toolkit.get_tools()
```

### Agents

By themselves, language models can't take actions - they just output text.
A big use case for LangChain is creating **agents**.
Agents are systems that use an LLM as a reasoning enginer to determine which actions to take and what the inputs to those actions should be.
The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.

[LangGraph](https://github.com/langchain-ai/langgraph) is an extension of LangChain specifically aimed at creating highly controllable and customizable agents.
Please check out that documentation for a more in depth overview of agent concepts.

There is a legacy agent concept in LangChain that we are moving towards deprecating: `AgentExecutor`.
AgentExecutor was essentially a runtime for agents.
It was a great place to get started, however, it was not flexible enough as you started to have more customized agents.
In order to solve that we built LangGraph to be this flexible, highly-controllable runtime.

If you are still using AgentExecutor, do not fear: we still have a guide on [how to use AgentExecutor](/docs/how_to/agent_executor).
It is recommended, however, that you start to transition to LangGraph.
In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent)