Flexible GraphRAG system supporting multiple LLM providers, graph databases, vector stores, and data sources
Project description
Flexible GraphRAG
Python package for the Flexible GraphRAG stack: document processing (Docling or LlamaParse), knowledge graphs, ontologies, many LLMs, GraphRAG and RAG, hybrid search (fulltext, vector, property graph, RDF/SPARQL), AI query, and AI chat. LlamaIndex and LangChain are peer frameworks (LlamaIndex defaults per pipeline stage). REST API via FastAPI; optional MCP server; Angular / React / Vue clients live in the monorepo.
Install: uv pip install flexible-graphrag (or uv pip install -e . from this directory). Optional stacks (LangChain, RDF extras, observability, Spanner, AGE, SurrealDB, Docling OCR, …) are only defined as [project.optional-dependencies] in pyproject.toml — not via a separate requirements-style file.
- Repository: github.com/stevereiner/flexible-graphrag
- Full README: README.md on GitHub
- Documentation: stevereiner.github.io/flexible-graphrag
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file flexible_graphrag-0.6.0.tar.gz.
File metadata
- Download URL: flexible_graphrag-0.6.0.tar.gz
- Upload date:
- Size: 542.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.17
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7b3d6629ac6a654a842275019e3b004e73d4ef068e3fd3f0f0964cdec1da7080
|
|
| MD5 |
c2b75c3bba20131e09be221f93958e4d
|
|
| BLAKE2b-256 |
c2f9faab9728869b1c253865fab2c69acafff99d43ff75050f48d5eba641410a
|
File details
Details for the file flexible_graphrag-0.6.0-py3-none-any.whl.
File metadata
- Download URL: flexible_graphrag-0.6.0-py3-none-any.whl
- Upload date:
- Size: 667.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.17
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
32def62ff6f42530ee6aaa45f2b824bd3aaf61c6921cf0e4536c873cacf99ff9
|
|
| MD5 |
e58330c22aeea6a97a906456a505579d
|
|
| BLAKE2b-256 |
eff5b58cd57913e3e6876849aea814478a55133c55cbee9bb3e3a8db41e391d0
|
