feat(notebook): add GraphRAG knowledge extraction from scratch#251
Open
abdelhadi703 wants to merge 1 commit intomistralai:mainfrom
Open
feat(notebook): add GraphRAG knowledge extraction from scratch#251abdelhadi703 wants to merge 1 commit intomistralai:mainfrom
abdelhadi703 wants to merge 1 commit intomistralai:mainfrom
Conversation
Build a complete GraphRAG pipeline using only Mistral AI SDK: - Entity/relationship extraction with Pydantic structured outputs - Knowledge graph construction with NetworkX - Hybrid retrieval combining FAISS vector search and graph traversal - Comparison of standard RAG vs GraphRAG on multi-hop questions
abdelhadi703
force-pushed
the
feat/graphrag-knowledge-extraction
branch
from
e315f89 to
d8d18c8
Compare
Author
|
Hi @mistralai/team, Bumping this GraphRAG notebook for review. It demonstrates knowledge graph extraction using Mistral models. Looking forward to your feedback. Thanks! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This notebook adds a complete GraphRAG pipeline built from scratch using only the Mistral AI SDK — no external graph databases required.
What's included:
Stack:
mistralai+networkx+faiss-cpu+pydantic+matplotlibWhy this matters:
The existing
camel_graph_rag.ipynbrequires CAMEL + Neo4j, making it hard to run on Colab. This notebook provides a lightweight, self-contained alternative that demonstrates GraphRAG concepts without external dependencies.Tested locally with
mistral-large-latestandmistral-embed.Checklist