👉 Use the GraphRAG Accelerator solution
👉 Microsoft Research Blog Post
👉 Read the docs
👉 GraphRAG Arxiv
The GraphRAG project is a data pipeline and transformation suite that is designed to extract meaningful, structured data from unstructured text using the power of LLMs.
To learn more about GraphRAG and how it can be used to enhance your LLM's ability to reason about your private data, please visit the Microsoft Research Blog Post.
分支feature/ollama-support上实现了支持Ollama免费大模型的调用，本地也可以玩了。
跟着教程走一遍
settings.yaml参考配置如下：
llm:
api_key: NONE
type: ollama_chat # or azure_openai_chat
model: llama3.1:8b
model_supports_json: false # recommended if this is available for your model.
max_tokens: 12800
api_base: http://localhost:11434
concurrent_requests: 2 # the number of parallel inflight requests that may be made
embeddings:
llm:
api_key: NONE
type: ollama_embedding # or azure_openai_embedding
model: nomic-embed-text:latest
api_base: http://localhost:11434
concurrent_requests: 2 # the number of parallel inflight requests that may be made