Nathan Evans comments

Results 142 comments of


                                            Nathan Evans

[Feature Request]: Drop in Solution with Azure Deployed OpenAI

Have you looked at the Solution Accelerator repo? https://github.com/Azure-Samples/graphrag-accelerator

Does it support streaming output?

Yes, if you use the `asearch` method and supply callbacks it should invoke your callback as new tokens are received from the LLM API

How can we create RAG dynamicly?

If you add new content to the input and _do _not__ change your indexing parameters, you should get the benefit of the cache on many of the requests. Changing parameters...

How can we create RAG dynamicly?

Consolidating index update requests with #741

[Bug]: JSON Decode Error

Consolidating alternate model issues here: #657

Consider adding an entity reconciliation step that merges nodes that seem to be duplicate

Closing as duplicate with #113 that is tracking our entity resolution feature

🔥我为GraphRAG实现了Open WebUI的接入

Linked in discussion https://github.com/microsoft/graphrag/discussions/697

Provide an option to fail fast when LLM calls timeout or are exhausted

Related to #811

[Feature Request]: <title> The model may generate a json string in markdown format

We have resolved several issues related to text encoding and JSON parsing that are rolled up into version [0.2.2](https://github.com/microsoft/graphrag/releases/tag/v0.2.2). Please try again with that version and re-open if this is...