graphrag
graphrag copied to clipboard
microsoft
A modular graph-based Retrieval-Augmented Generation (RAG) system
I attempted to conduct an RAG test using Qian Zhongshu's "Fortress Besieged" and encountered the following errors. the pipeline msg： ``` ❌ create_final_community_reports None ⠋ GraphRAG Indexer ├── Loading Input...
it just used $15 for a very small amount of text to index on openai API. Is there any solution to reduce cost for this ? I was just testing...
I am currently facing a challenge with adding new text to RAG. My current approach involves reinitializing the entire RAG, which is slow. Please provide guidance or suggestions on efficiently...
The published paper has a few example pictures showcasing the graph in a visualized way and i think it would be very valuable to be able to get a similar...
I did not see the streaming output configuration on your official doc. Does this project support stream output when using LocalSearch?
 [indexing-engine.log](https://github.com/user-attachments/files/16130639/indexing-engine.log) please help me to solve the issue, why always happen.
book.txt has about one million words, and there was an error during the final stage of execution ``` 23:17:40,280 datashaper.workflow.workflow ERROR Error executing verb "text_embed" in create_final_entities: setting an array...
Error executing verb "cluster_graph" in create_base_entity_graph: Columns must be same length as key
This is my configuration: ``` encoding_model: cl100k_base skip_workflows: [] llm: api_key: lm-studio type: openai_chat # or azure_openai_chat model: bartowski/gemma-2-9b-it-GGUF/gemma-2-9b-it-Q6_K-Q8.gguf model_supports_json: true # recommended if this is available for your model....
result = await search_engine.asearch("Tell me about Agent Mercer") print(result.response) asearch() is not returning and is still executing
