| Name | langchain-graph-retriever JSON |
| Version |
0.4.2
JSON |
| download |
| home_page | None |
| Summary | LangChain retriever for traversing document graphs on top of vector-based similarity search. |
| upload_time | 2025-02-07 21:00:47 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | None |
| keywords |
rag
graph rag
langchain
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# LangChain Graph Retriever
LangChain Graph Retriever is a Python library that supports traversing a document graph on top of vector-based similarity search.
It works seamlessly with LangChain's retriever framework and supports various graph traversal strategies for efficient document discovery.
## Features
- **Vector Search**: Perform similarity searches using vector embeddings.
- **Graph Traversal**: Apply traversal strategies such as breadth-first (Eager) or Maximal Marginal Relevance (MMR) to explore document relationships.
- **Customizable Strategies**: Easily extend and configure traversal strategies to meet your specific use case.
- **Multiple Adapters**: Support for various vector stores, including AstraDB, Cassandra, Chroma, OpenSearch, and in-memory storage.
- **Synchronous and Asynchronous Retrieval**: Supports both sync and async workflows for flexibility in different applications.
## Installation
Install the library via pip:
```bash
pip install langchain-graph-retriever
```
## Getting Started
Here is an example of how to use LangChain Graph Retriever:
```python
from langchain_graph_retriever import GraphRetriever
from langchain_core.vectorstores import Chroma
# Initialize the vector store (Chroma in this example)
vector_store = Chroma(embedding_function=your_embedding_function)
# Create the Graph Retriever
retriever = GraphRetriever(
store=vector_store,
# Define edges based on document metadata
edges=[("keywords", "keywords")],
)
# Perform a retrieval
documents = retriever.retrieve("What is the capital of France?")
# Print the results
for doc in documents:
print(doc.page_content)
```
## License
This project is licensed under the Apache 2 License. See the LICENSE file for more details.
Raw data
{
"_id": null,
"home_page": null,
"name": "langchain-graph-retriever",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "RAG, graph RAG, langchain",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/d2/dd/d09fcfb785a7ed5641aa3bf1bb4a2cd33421d32cf5b66062b99cc8ea9dde/langchain_graph_retriever-0.4.2.tar.gz",
"platform": null,
"description": "# LangChain Graph Retriever\n\nLangChain Graph Retriever is a Python library that supports traversing a document graph on top of vector-based similarity search.\nIt works seamlessly with LangChain's retriever framework and supports various graph traversal strategies for efficient document discovery.\n\n## Features\n\n- **Vector Search**: Perform similarity searches using vector embeddings.\n- **Graph Traversal**: Apply traversal strategies such as breadth-first (Eager) or Maximal Marginal Relevance (MMR) to explore document relationships.\n- **Customizable Strategies**: Easily extend and configure traversal strategies to meet your specific use case.\n- **Multiple Adapters**: Support for various vector stores, including AstraDB, Cassandra, Chroma, OpenSearch, and in-memory storage.\n- **Synchronous and Asynchronous Retrieval**: Supports both sync and async workflows for flexibility in different applications.\n\n## Installation\n\nInstall the library via pip:\n\n```bash\npip install langchain-graph-retriever\n```\n\n## Getting Started\n\nHere is an example of how to use LangChain Graph Retriever:\n\n```python\nfrom langchain_graph_retriever import GraphRetriever\nfrom langchain_core.vectorstores import Chroma\n\n# Initialize the vector store (Chroma in this example)\nvector_store = Chroma(embedding_function=your_embedding_function)\n\n# Create the Graph Retriever\nretriever = GraphRetriever(\n store=vector_store,\n # Define edges based on document metadata\n edges=[(\"keywords\", \"keywords\")],\n)\n\n# Perform a retrieval\ndocuments = retriever.retrieve(\"What is the capital of France?\")\n\n# Print the results\nfor doc in documents:\n print(doc.page_content)\n```\n\n## License\n\nThis project is licensed under the Apache 2 License. See the LICENSE file for more details.\n",
"bugtrack_url": null,
"license": null,
"summary": "LangChain retriever for traversing document graphs on top of vector-based similarity search.",
"version": "0.4.2",
"project_urls": {
"Bug Reports": "https://github.com/datastax/graph-rag/issues",
"GitHub": "https://github.com/datastax/graph-rag",
"Homepage": "https://datastax.github.io/graph-rag"
},
"split_keywords": [
"rag",
" graph rag",
" langchain"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2f0e6d76d95db025949efd3f6489dd6dc70b4ab6c269a8d468d337877fb13c16",
"md5": "4108335b6bd37b487e79e097f4d65040",
"sha256": "421cf890c040e92b6045303fbeefc39578caa2906589b10c0cad46d0da4e80ea"
},
"downloads": -1,
"filename": "langchain_graph_retriever-0.4.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4108335b6bd37b487e79e097f4d65040",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 34512,
"upload_time": "2025-02-07T21:00:45",
"upload_time_iso_8601": "2025-02-07T21:00:45.992794Z",
"url": "https://files.pythonhosted.org/packages/2f/0e/6d76d95db025949efd3f6489dd6dc70b4ab6c269a8d468d337877fb13c16/langchain_graph_retriever-0.4.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d2ddd09fcfb785a7ed5641aa3bf1bb4a2cd33421d32cf5b66062b99cc8ea9dde",
"md5": "1567d3a0bf9f4703e740cd8db37409b3",
"sha256": "479019b9de7a40c5258e9e93e0b10b431811ebd6ce9af3852c83964c813b6a0d"
},
"downloads": -1,
"filename": "langchain_graph_retriever-0.4.2.tar.gz",
"has_sig": false,
"md5_digest": "1567d3a0bf9f4703e740cd8db37409b3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 33466,
"upload_time": "2025-02-07T21:00:47",
"upload_time_iso_8601": "2025-02-07T21:00:47.809205Z",
"url": "https://files.pythonhosted.org/packages/d2/dd/d09fcfb785a7ed5641aa3bf1bb4a2cd33421d32cf5b66062b99cc8ea9dde/langchain_graph_retriever-0.4.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-07 21:00:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "datastax",
"github_project": "graph-rag",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "langchain-graph-retriever"
}
