mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-26 09:53:41 +00:00
community: add Needle retriever and document loader integration (#28157)
- [x] **PR title**: "community: add Needle retriever and document loader
integration"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: add foobar LLM"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** This PR adds a new integration for Needle, which
includes:
- **NeedleRetriever**: A retriever for fetching documents from Needle
collections.
- **NeedleLoader**: A document loader for managing and loading documents
into Needle collections.
- Example notebooks demonstrating usage have been added in:
- `docs/docs/integrations/retrievers/needle.ipynb`
- `docs/docs/integrations/document_loaders/needle.ipynb`.
- **Dependencies:** The `needle-python` package is required as an
external dependency for accessing Needle's API. It has been added to the
extended testing dependencies list.
- **Twitter handle:** Feel free to mention me if this PR gets announced:
[needlexai](https://x.com/NeedlexAI).
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. Unit tests have been added for both `NeedleRetriever` and
`NeedleLoader` in `libs/community/tests/unit_tests`. These tests mock
API calls to avoid relying on network access.
2. Example notebooks have been added to `docs/docs/integrations/`,
showcasing both retriever and loader functionality.
- [x] **Lint and test**: Run `make format`, `make lint`, and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
- `make format`: Passed
- `make lint`: Passed
- `make test`: Passed (requires `needle-python` to be installed locally;
this package is not added to LangChain dependencies).
Additional guidelines:
- [x] Optional dependencies are imported only within functions.
- [x] No dependencies have been added to pyproject.toml files except for
those required for unit tests.
- [x] The PR does not touch more than one package.
- [x] Changes are fully backwards compatible.
- [x] Community additions are not re-imported into LangChain core.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Jan Heimes
GitHub
253
docs/docs/integrations/document_loaders/needle.ipynb
Normal file
253
docs/docs/integrations/document_loaders/needle.ipynb
Normal file
@@ -0,0 +1,253 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Needle Document Loader\n",
|
||||
"[Needle](https://needle-ai.com) makes it easy to create your RAG pipelines with minimal effort. \n",
|
||||
"\n",
|
||||
"For more details, refer to our [API documentation](https://docs.needle-ai.com/docs/api-reference/needle-api)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Overview\n",
|
||||
"The Needle Document Loader is a utility for integrating Needle collections with LangChain. It enables seamless storage, retrieval, and utilization of documents for Retrieval-Augmented Generation (RAG) workflows.\n",
|
||||
"\n",
|
||||
"This example demonstrates:\n",
|
||||
"\n",
|
||||
"* Storing documents into a Needle collection.\n",
|
||||
"* Setting up a retriever to fetch documents.\n",
|
||||
"* Building a Retrieval-Augmented Generation (RAG) pipeline."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup\n",
|
||||
"Before starting, ensure you have the following environment variables set:\n",
|
||||
"\n",
|
||||
"* NEEDLE_API_KEY: Your API key for authenticating with Needle.\n",
|
||||
"* OPENAI_API_KEY: Your OpenAI API key for language model operations."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"NEEDLE_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialization\n",
|
||||
"To initialize the NeedleLoader, you need the following parameters:\n",
|
||||
"\n",
|
||||
"* needle_api_key: Your Needle API key (or set it as an environment variable).\n",
|
||||
"* collection_id: The ID of the Needle collection to work with."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Instantiation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders.needle import NeedleLoader\n",
|
||||
"\n",
|
||||
"collection_id = \"clt_01J87M9T6B71DHZTHNXYZQRG5H\"\n",
|
||||
"\n",
|
||||
"# Initialize NeedleLoader to store documents to the collection\n",
|
||||
"document_loader = NeedleLoader(\n",
|
||||
" needle_api_key=os.getenv(\"NEEDLE_API_KEY\"),\n",
|
||||
" collection_id=collection_id,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load\n",
|
||||
"To add files to the Needle collection:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"files = {\n",
|
||||
" \"tech-radar-30.pdf\": \"https://www.thoughtworks.com/content/dam/thoughtworks/documents/radar/2024/04/tr_technology_radar_vol_30_en.pdf\"\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"document_loader.add_files(files=files)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Show the documents in the collection\n",
|
||||
"# collections_documents = document_loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Lazy Load\n",
|
||||
"The lazy_load method allows you to iteratively load documents from the Needle collection, yielding each document as it is fetched:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Show the documents in the collection\n",
|
||||
"# collections_documents = document_loader.lazy_load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage\n",
|
||||
"### Use within a chain\n",
|
||||
"Below is a complete example of setting up a RAG pipeline with Needle within a chain:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': 'Did RAG move to accepted?',\n",
|
||||
" 'context': [Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.')],\n",
|
||||
" 'answer': 'Yes, RAG has been adopted as the preferred pattern for improving the quality of responses generated by a large language model.'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"from langchain.chains import create_retrieval_chain\n",
|
||||
"from langchain.chains.combine_documents import create_stuff_documents_chain\n",
|
||||
"from langchain_community.retrievers.needle import NeedleRetriever\n",
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"from langchain_openai import ChatOpenAI\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"# Initialize the Needle retriever (make sure your Needle API key is set as an environment variable)\n",
|
||||
"retriever = NeedleRetriever(\n",
|
||||
" needle_api_key=os.getenv(\"NEEDLE_API_KEY\"),\n",
|
||||
" collection_id=\"clt_01J87M9T6B71DHZTHNXYZQRG5H\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Define system prompt for the assistant\n",
|
||||
"system_prompt = \"\"\"\n",
|
||||
" You are an assistant for question-answering tasks. \n",
|
||||
" Use the following pieces of retrieved context to answer the question.\n",
|
||||
" If you don't know, say so concisely.\\n\\n{context}\n",
|
||||
" \"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(\n",
|
||||
" [(\"system\", system_prompt), (\"human\", \"{input}\")]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Define the question-answering chain using a document chain (stuff chain) and the retriever\n",
|
||||
"question_answer_chain = create_stuff_documents_chain(llm, prompt)\n",
|
||||
"\n",
|
||||
"# Create the RAG (Retrieval-Augmented Generation) chain by combining the retriever and the question-answering chain\n",
|
||||
"rag_chain = create_retrieval_chain(retriever, question_answer_chain)\n",
|
||||
"\n",
|
||||
"# Define the input query\n",
|
||||
"query = {\"input\": \"Did RAG move to accepted?\"}\n",
|
||||
"\n",
|
||||
"response = rag_chain.invoke(query)\n",
|
||||
"\n",
|
||||
"response"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"For detailed documentation of all `Needle` features and configurations head to the API reference: https://docs.needle-ai.com"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"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": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
235
docs/docs/integrations/retrievers/needle.ipynb
Normal file
235
docs/docs/integrations/retrievers/needle.ipynb
Normal file
@@ -0,0 +1,235 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Needle Retriever\n",
|
||||
"[Needle](https://needle-ai.com) makes it easy to create your RAG pipelines with minimal effort. \n",
|
||||
"\n",
|
||||
"For more details, refer to our [API documentation](https://docs.needle-ai.com/docs/api-reference/needle-api)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Overview\n",
|
||||
"The Needle Document Loader is a utility for integrating Needle collections with LangChain. It enables seamless storage, retrieval, and utilization of documents for Retrieval-Augmented Generation (RAG) workflows.\n",
|
||||
"\n",
|
||||
"This example demonstrates:\n",
|
||||
"\n",
|
||||
"* Storing documents into a Needle collection.\n",
|
||||
"* Setting up a retriever to fetch documents.\n",
|
||||
"* Building a Retrieval-Augmented Generation (RAG) pipeline."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup\n",
|
||||
"Before starting, ensure you have the following environment variables set:\n",
|
||||
"\n",
|
||||
"* NEEDLE_API_KEY: Your API key for authenticating with Needle.\n",
|
||||
"* OPENAI_API_KEY: Your OpenAI API key for language model operations."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialization\n",
|
||||
"To initialize the NeedleLoader, you need the following parameters:\n",
|
||||
"\n",
|
||||
"* needle_api_key: Your Needle API key (or set it as an environment variable).\n",
|
||||
"* collection_id: The ID of the Needle collection to work with."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"NEEDLE_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Instantiation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders.needle import NeedleLoader\n",
|
||||
"\n",
|
||||
"collection_id = \"clt_01J87M9T6B71DHZTHNXYZQRG5H\"\n",
|
||||
"\n",
|
||||
"# Initialize NeedleLoader to store documents to the collection\n",
|
||||
"document_loader = NeedleLoader(\n",
|
||||
" needle_api_key=os.getenv(\"NEEDLE_API_KEY\"),\n",
|
||||
" collection_id=collection_id,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load\n",
|
||||
"To add files to the Needle collection:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"files = {\n",
|
||||
" \"tech-radar-30.pdf\": \"https://www.thoughtworks.com/content/dam/thoughtworks/documents/radar/2024/04/tr_technology_radar_vol_30_en.pdf\"\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"document_loader.add_files(files=files)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Show the documents in the collection\n",
|
||||
"# collections_documents = document_loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage\n",
|
||||
"### Use within a chain\n",
|
||||
"Below is a complete example of setting up a RAG pipeline with Needle within a chain:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': 'Did RAG move to accepted?',\n",
|
||||
" 'context': [Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='New Moved in/out No change\\n\\n© Thoughtworks, Inc. All Rights Reserved. 12\\n\\nTechniques\\n\\n1. Retrieval-augmented generation (RAG)\\nAdopt\\n\\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \\nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \\nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \\ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \\ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \\na given prompt, the database is queried to retrieve relevant documents, which are then combined \\nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \\nreduced hallucinations. The context window — which determines the maximum size of the LLM input \\n— is limited, which means that selecting the most relevant documents is crucial. We improve the \\nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \\ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \\na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),\n",
|
||||
" Document(metadata={}, page_content='https://www.thoughtworks.com/radar/tools/nemo-guardrails\\nhttps://www.thoughtworks.com/radar/platforms/langfuse\\nhttps://www.thoughtworks.com/radar/techniques/retrieval-augmented-generation-rag\\nhttps://cruisecontrol.sourceforge.net/\\nhttps://martinfowler.com/articles/continuousIntegration.html\\nhttps://www.thoughtworks.com/radar/techniques/peer-review-equals-pull-request\\nhttps://martinfowler.com/bliki/ContinuousIntegrationCertification.html\\nhttps://linearb.io/platform/gitstream\\nhttps://www.thoughtworks.com/radar/tools/github-merge-queue\\nhttps://stacking.dev/\\n\\n© Thoughtworks, Inc. All Rights Reserved. 8\\n\\nHold HoldAssess AssessTrial TrialAdopt Adopt\\n\\n18\\n\\n8\\n\\n24\\n\\n29\\n\\n30\\n31\\n\\n32\\n33\\n\\n34 35\\n\\n36\\n37\\n\\n38 39\\n\\n40\\n41\\n\\n42\\n43\\n\\n26\\n\\n2\\n\\n3\\n\\n4\\n\\n5\\n\\n6 7\\n\\n9\\n\\n15\\n\\n16\\n\\n17\\n\\n10\\n\\n11\\n\\n12\\n\\n13 14\\n\\n44\\n\\n47\\n49\\n\\n50\\n\\n65\\n66\\n\\n67 68\\n69\\n\\n70\\n71\\n\\n72\\n\\n73 74\\n\\n75\\n\\n76 77\\n\\n78\\n79\\n\\n80\\n81\\n\\n82\\n\\n83\\n\\n51\\n\\n52 54\\n\\n59\\n\\n53\\n56\\n\\n58\\n\\n61\\n\\n62\\n63\\n\\n64\\n\\n85\\n\\n88 89\\n\\n90 91\\n\\n92\\n93\\n\\n94\\n95 96\\n\\n97\\n\\n98 99\\n\\n100\\n\\n101\\n102\\n\\n103\\n\\n104\\n\\n86\\n\\n87\\n1921\\n\\n22\\n\\n20\\n28\\n\\n25\\n\\n27\\n\\n23\\n\\n84\\n\\n105\\n\\n1\\n45\\n\\n46\\n\\n48\\n\\n55\\n57')],\n",
|
||||
" 'answer': 'Yes, RAG has moved to the \"Adopt\" status.'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"from langchain.chains import create_retrieval_chain\n",
|
||||
"from langchain.chains.combine_documents import create_stuff_documents_chain\n",
|
||||
"from langchain_community.retrievers.needle import NeedleRetriever\n",
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"from langchain_openai import ChatOpenAI\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"\n",
|
||||
"# Initialize the Needle retriever (make sure your Needle API key is set as an environment variable)\n",
|
||||
"retriever = NeedleRetriever(\n",
|
||||
" needle_api_key=os.getenv(\"NEEDLE_API_KEY\"),\n",
|
||||
" collection_id=\"clt_01J87M9T6B71DHZTHNXYZQRG5H\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Define system prompt for the assistant\n",
|
||||
"system_prompt = \"\"\"\n",
|
||||
" You are an assistant for question-answering tasks. \n",
|
||||
" Use the following pieces of retrieved context to answer the question.\n",
|
||||
" If you don't know, say so concisely.\\n\\n{context}\n",
|
||||
" \"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(\n",
|
||||
" [(\"system\", system_prompt), (\"human\", \"{input}\")]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Define the question-answering chain using a document chain (stuff chain) and the retriever\n",
|
||||
"question_answer_chain = create_stuff_documents_chain(llm, prompt)\n",
|
||||
"\n",
|
||||
"# Create the RAG (Retrieval-Augmented Generation) chain by combining the retriever and the question-answering chain\n",
|
||||
"rag_chain = create_retrieval_chain(retriever, question_answer_chain)\n",
|
||||
"\n",
|
||||
"# Define the input query\n",
|
||||
"query = {\"input\": \"Did RAG move to accepted?\"}\n",
|
||||
"\n",
|
||||
"response = rag_chain.invoke(query)\n",
|
||||
"\n",
|
||||
"response"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"For detailed documentation of all `Needle` features and configurations head to the API reference: https://docs.needle-ai.com"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"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": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
Reference in New Issue
Block a user