Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

template readme's in docs (#13152)

Browse Source
pull/13178/head
Bagatur 7 months ago committed by GitHub
parent 86b93b5810
commit dd7959f4ac
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 272 additions and 213 deletions
Show Stats Download Patch File Download Diff File

1
.gitignore vendored
Unescape Escape View File

@ -178,3 +178,4 @@ docs/docs/build
docs/docs/node_modules
docs/docs/yarn.lock
_dist
docs/docs/templates

428
docs/docs/integrations/llms/huggingface_pipelines.ipynb
Unescape Escape View File

@ -1,214 +1,218 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "959300d4",
"metadata": {},
"source": [
"# Hugging Face Local Pipelines\n",
"\n",
"Hugging Face models can be run locally through the `HuggingFacePipeline` class.\n",
"\n",
"The [Hugging Face Model Hub](https://huggingface.co/models) hosts over 120k models, 20k datasets, and 50k demo apps (Spaces), all open source and publicly available, in an online platform where people can easily collaborate and build ML together.\n",
"\n",
"These can be called from LangChain either through this local pipeline wrapper or by calling their hosted inference endpoints through the HuggingFaceHub class. For more information on the hosted pipelines, see the [HuggingFaceHub](huggingface_hub.html) notebook."
]
"cells": [
{
"cell_type": "markdown",
"id": "959300d4",
"metadata": {},
"source": [
"# Hugging Face Local Pipelines\n",
"\n",
"Hugging Face models can be run locally through the `HuggingFacePipeline` class.\n",
"\n",
"The [Hugging Face Model Hub](https://huggingface.co/models) hosts over 120k models, 20k datasets, and 50k demo apps (Spaces), all open source and publicly available, in an online platform where people can easily collaborate and build ML together.\n",
"\n",
"These can be called from LangChain either through this local pipeline wrapper or by calling their hosted inference endpoints through the HuggingFaceHub class. For more information on the hosted pipelines, see the [HuggingFaceHub](huggingface_hub.html) notebook."
]
},
{
"cell_type": "markdown",
"id": "4c1b8450-5eaf-4d34-8341-2d785448a1ff",
"metadata": {
"tags": []
},
"source": [
"To use, you should have the ``transformers`` python [package installed](https://pypi.org/project/transformers/), as well as [pytorch](https://pytorch.org/get-started/locally/). You can also install `xformer` for a more memory-efficient attention implementation."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d772b637-de00-4663-bd77-9bc96d798db2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install transformers --quiet"
]
},
{
"cell_type": "markdown",
"id": "91ad075f-71d5-4bc8-ab91-cc0ad5ef16bb",
"metadata": {},
"source": [
"### Model Loading\n",
"\n",
"Models can be loaded by specifying the model parameters using the `from_model_id` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "165ae236-962a-4763-8052-c4836d78a5d2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
"\n",
"hf = HuggingFacePipeline.from_model_id(\n",
" model_id=\"gpt2\",\n",
" task=\"text-generation\",\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")"
]
},
{
"cell_type": "markdown",
"id": "00104b27-0c15-4a97-b198-4512337ee211",
"metadata": {},
"source": [
"They can also be loaded by passing in an existing `transformers` pipeline directly"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
"\n",
"model_id = \"gpt2\"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
"model = AutoModelForCausalLM.from_pretrained(model_id)\n",
"pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=10)\n",
"hf = HuggingFacePipeline(pipeline=pipe)"
],
"id": "7f426a4f"
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Chain\n",
"\n",
"With the model loaded into memory, you can compose it with a prompt to\n",
"form a chain."
],
"id": "60e7ba8d"
},
{
"cell_type": "code",
"execution_count": null,
"id": "3acf0069",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"\n",
"template = \"\"\"Question: {question}\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"prompt = PromptTemplate.from_template(template)\n",
"\n",
"chain = prompt | hf\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(chain.invoke({\"question\": question}))"
]
},
{
"cell_type": "markdown",
"id": "dbbc3a37",
"metadata": {},
"source": [
"### GPU Inference\n",
"\n",
"When running on a machine with GPU, you can specify the `device=n` parameter to put the model on the specified device.\n",
"Defaults to `-1` for CPU inference.\n",
"\n",
"If you have multiple-GPUs and/or the model is too large for a single GPU, you can specify `device_map=\"auto\"`, which requires and uses the [Accelerate](https://huggingface.co/docs/accelerate/index) library to automatically determine how to load the model weights. \n",
"\n",
"*Note*: both `device` and `device_map` should not be specified together and can lead to unexpected behavior."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gpu_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"gpt2\",\n",
" task=\"text-generation\",\n",
" device=0, # replace with device_map=\"auto\" to use the accelerate library.\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")\n",
"\n",
"gpu_chain = prompt | gpu_llm\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(gpu_chain.invoke({\"question\": question}))"
],
"id": "703c91c8"
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Batch GPU Inference\n",
"\n",
"If running on a device with GPU, you can also run inference on the GPU in batch mode."
],
"id": "59276016"
},
{
"cell_type": "code",
"execution_count": null,
"id": "097ba62f",
"metadata": {},
"outputs": [],
"source": [
"gpu_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"bigscience/bloom-1b7\",\n",
" task=\"text-generation\",\n",
" device=0, # -1 for CPU\n",
" batch_size=2, # adjust as needed based on GPU map and model size.\n",
" model_kwargs={\"temperature\": 0, \"max_length\": 64},\n",
")\n",
"\n",
"gpu_chain = prompt | gpu_llm.bind(stop=[\"\\n\\n\"])\n",
"\n",
"questions = []\n",
"for i in range(4):\n",
" questions.append({\"question\": f\"What is the number {i} in french?\"})\n",
"\n",
"answers = gpu_chain.batch(questions)\n",
"for answer in answers:\n",
" print(answer)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.5"
}
},
{
"cell_type": "markdown",
"id": "4c1b8450-5eaf-4d34-8341-2d785448a1ff",
"metadata": {
"tags": []
},
"source": [
"To use, you should have the ``transformers`` python [package installed](https://pypi.org/project/transformers/), as well as [pytorch](https://pytorch.org/get-started/locally/). You can also install `xformer` for a more memory-efficient attention implementation."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d772b637-de00-4663-bd77-9bc96d798db2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install transformers --quiet"
]
},
{
"cell_type": "markdown",
"id": "91ad075f-71d5-4bc8-ab91-cc0ad5ef16bb",
"metadata": {},
"source": [
"### Model Loading\n",
"\n",
"Models can be loaded by specifying the model parameters using the `from_model_id` method."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "165ae236-962a-4763-8052-c4836d78a5d2",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
"\n",
"hf = HuggingFacePipeline.from_model_id(\n",
" model_id=\"gpt2\",\n",
" task=\"text-generation\",\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")"
]
},
{
"cell_type": "markdown",
"id": "00104b27-0c15-4a97-b198-4512337ee211",
"metadata": {},
"source": [
"They can also be loaded by passing in an existing `transformers` pipeline directly"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
"\n",
"model_id = \"gpt2\"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
"model = AutoModelForCausalLM.from_pretrained(model_id)\n",
"pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=10)\n",
"hf = HuggingFacePipeline(pipeline=pipe)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Chain\n",
"\n",
"With the model loaded into memory, you can compose it with a prompt to\n",
"form a chain."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3acf0069",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"\n",
"template = \"\"\"Question: {question}\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"prompt = PromptTemplate.from_template(template)\n",
"\n",
"chain = prompt | hf\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(chain.invoke({\"question\": question}))"
]
},
{
"cell_type": "markdown",
"id": "dbbc3a37",
"metadata": {},
"source": [
"### GPU Inference\n",
"\n",
"When running on a machine with GPU, you can specify the `device=n` parameter to put the model on the specified device.\n",
"Defaults to `-1` for CPU inference.\n",
"\n",
"If you have multiple-GPUs and/or the model is too large for a single GPU, you can specify `device_map=\"auto\"`, which requires and uses the [Accelerate](https://huggingface.co/docs/accelerate/index) library to automatically determine how to load the model weights. \n",
"\n",
"*Note*: both `device` and `device_map` should not be specified together and can lead to unexpected behavior."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gpu_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"gpt2\",\n",
" task=\"text-generation\",\n",
" device=0, # replace with device_map=\"auto\" to use the accelerate library.\n",
" pipeline_kwargs={\"max_new_tokens\": 10},\n",
")\n",
"\n",
"gpu_chain = prompt | gpu_llm\n",
"\n",
"question = \"What is electroencephalography?\"\n",
"\n",
"print(gpu_chain.invoke({\"question\": question}))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Batch GPU Inference\n",
"\n",
"If running on a device with GPU, you can also run inference on the GPU in batch mode."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "097ba62f",
"metadata": {},
"outputs": [],
"source": [
"gpu_llm = HuggingFacePipeline.from_model_id(\n",
" model_id=\"bigscience/bloom-1b7\",\n",
" task=\"text-generation\",\n",
" device=0, # -1 for CPU\n",
" batch_size=2, # adjust as needed based on GPU map and model size.\n",
" model_kwargs={\"temperature\": 0, \"max_length\": 64},\n",
")\n",
"\n",
"gpu_chain = prompt | gpu_llm.bind(stop=[\"\\n\\n\"])\n",
"\n",
"questions = []\n",
"for i in range(4):\n",
" questions.append({\"question\": f\"What is the number {i} in french?\"})\n",
"\n",
"answers = gpu_chain.batch(questions)\n",
"for answer in answers:\n",
" print(answer)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
"nbformat": 4,
"nbformat_minor": 5
}

5
docs/docusaurus.config.js
Unescape Escape View File

@ -175,6 +175,11 @@ const config = {
label: "More",
position: "left",
items: [
{
type: "docSidebar",
sidebarId: "templates",
label: "Templates",
},
{
to: "/docs/community",
label: "Community",

36
docs/scripts/copy_templates.py
Unescape Escape View File

@ -0,0 +1,36 @@
import glob
import os
from pathlib import Path
import re
import shutil
TEMPLATES_DIR = Path(os.path.abspath(__file__)).parents[2] / "templates"
DOCS_TEMPLATES_DIR = Path(os.path.abspath(__file__)).parents[1] / "docs" / "templates"
readmes = list(glob.glob(str(TEMPLATES_DIR) + "/*/README.md"))
destinations = [readme[len(str(TEMPLATES_DIR)) + 1:-10] + ".md" for readme in readmes]
for source, destination in zip(readmes, destinations):
full_destination = DOCS_TEMPLATES_DIR / destination
shutil.copyfile(source, full_destination)
with open(full_destination, "r") as f:
content = f.read()
# remove images
content = re.sub("\!\[.*?\]\((.*?)\)", "", content)
with open(full_destination, "w") as f:
f.write(content)
sidebar_hidden = """---
sidebar_class_name: hidden
---
"""
TEMPLATES_INDEX_DESTINATION = DOCS_TEMPLATES_DIR / "index.md"
with open(TEMPLATES_INDEX_DESTINATION, "r") as f:
content = f.read()
# replace relative links
content = re.sub("\]\(\.\.\/", "](/docs/templates/", content)
with open(TEMPLATES_INDEX_DESTINATION, "w") as f:
f.write(sidebar_hidden + content)

10
docs/sidebars.js
Unescape Escape View File

@ -123,4 +123,14 @@ module.exports = {
guides: [
{type: "autogenerated", dirName: "guides" }
],
templates: [
{
type: "category",
label: "Templates",
items: [
{ type: "autogenerated", dirName: "templates" },
],
link: { type: 'doc', id: "templates/index" }
},
],
};

5
docs/vercel_build.sh
Unescape Escape View File

@ -47,8 +47,11 @@ source .venv/bin/activate
python3.11 -m pip install --upgrade pip
python3.11 -m pip install -r vercel_requirements.txt
python3.11 scripts/model_feat_table.py
nbdoc_build --srcdir docs
mkdir docs/templates
cp ../templates/docs/INDEX.md docs/templates/index.md
python3.11 scripts/copy_templates.py
cp ../cookbook/README.md src/pages/cookbook.mdx
cp ../.github/CONTRIBUTING.md docs/contributing.md
wget https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O docs/langserve.md
nbdoc_build --srcdir docs
python3.11 scripts/generate_api_reference_links.py

Write Preview
Loading…
Cancel
Save