microsoft / graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system
https://microsoft.github.io/graphrag/
MIT License
16.78k stars 1.58k forks source link

[Issue]: <Errors occurred during the pipeline run> #622

Closed FlypigW closed 1 month ago

FlypigW commented 1 month ago

Describe the issue

❌ create_base_entity_graph None
⠸ GraphRAG Indexer ├── Loading Input (text) - 1 files loaded (0 filtered) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00 0:00:00 ├── create_base_text_units ├── create_base_extracted_entities ├── create_summarized_entities └── create_base_entity_graph ❌ Errors occurred during the pipeline run, see logs for more details.

model: gemma2 embedding model: nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.Q4_K_M.gguf

Steps to reproduce

No response

GraphRAG Config Used

No response

Logs and screenshots

indexing-engine.log

Additional Information

rushizirpe commented 1 month ago

As you can see on LINE #395 in indexing-engine.log you have provided, there's an openai.AuthenticationError saying invalid API key. Please cross-check OPEN_API_KEY in environment variables.

If you want to use open-source models, I've put together a repository for deploying models from HuggingFace to local endpoints, having similar functionality to OpenAI APIs. Here’s the link to the repo: https://github.com/rushizirpe/open-llm-server

Alternatively, I have created a Colab notebook for Graphrag: https://colab.research.google.com/drive/1uhFDnih1WKrSRQHisU-L6xw6coapgR51?usp=sharing In Notebook, you will need GROQ_API_KEY if you don't have access to GPUs like A100. You can get it from here: https://console.groq.com/keys

natoverse commented 1 month ago

Consolidating alternate model issues here: https://github.com/microsoft/graphrag/issues/657

yinzih commented 3 days ago

image 请问,这个问题解决了嘛?