nano-graphrag

nano-graphrag copied to clipboard

sometimes, while using nano-graphrag, the progress stuck while doing Entity Extraction process. while stuck, the output of terminal looks like below: ``` "Processed 26 chunks, 378 entities found(duplicated), 263 relations(duplicated)"...

Greenhub-1215

### Issue Hello, I have a similar error with #57 using no_openai_key_at_all.py. I already used qwen2:ctx32k to replace qwen2. How could I fix this problem? Thanks. ### Error ``` ⠹...

ericskh2

feat: add RedisKVStorage, MilvusVectorStorage, and NebulaGraphStorage

2

- Implement RedisKVStorage for key-value storage. - Implement MilvusVectorStorage for vector storage. - Implement NebulaGraphStorage for graph storage. Refer to #9 - Add tests for NebulaGraphStorage to ensure functionality. TODO...

utopia2077

Feature: prompt tuning

4

Hello ! Great project, so much easy to understand/hack than the microsoft one Is there any plan to support the prompt tuning feature ? https://microsoft.github.io/graphrag/posts/prompt_tuning/overview/ It would be really nice...

bdecarne

国内小伙伴微信群聊

10

 大家可以加这个群 沟通更直接一些

gusye1234

i want using Qwen 2 proved by Together but it not for Json format, how to i use it ?

1

my error: `BadRequestError Traceback (most recent call last) Cell In[10], [line 5](vscode-notebook-cell:?execution_count=10&line=5) [3](vscode-notebook-cell:?execution_count=10&line=3) nest_asyncio.apply() [4](vscode-notebook-cell:?execution_count=10&line=4) import asyncio ----> [5](vscode-notebook-cell:?execution_count=10&line=5) rag.insert(FAKE_TEXT) File ~/test/nano_graphrag/graphrag.py:217, in GraphRAG.insert(self, string_or_strings) [215](https://vscode-remote+ssh-002dremote-002b103-002e183-002e119-002e49.vscode-resource.vscode-cdn.net/root/test/~/test/nano_graphrag/graphrag.py:215) def insert(self, string_or_strings): [216](https://vscode-remote+ssh-002dremote-002b103-002e183-002e119-002e49.vscode-resource.vscode-cdn.net/root/test/~/test/nano_graphrag/graphrag.py:216)...

dangyuuki123

When the code would use the best_model_func, cheap_model_func and embedding_func separately?

1

ink7-sudo

Why is there repetitive content in the prompt

3

For example the Goal and Target response length and format repeated. Is this intentional repetition or some kind of error? PROMPTS[ "local_rag_response" ] = """---Role--- You are a helpful assistant...

knightmarehs

It's possible for the cache response cache to have null values

2

See `TypeError: unsupported operand type(s) for +=: 'NoneType' and 'str'` when writing graph Not sure exactly how to reproduce, flaky behavior when using large corpus with azure openai.

rawsh-rubrik

[Feature Request] For a real world application

5

Must have for real world application: 1) To actually use this in any application we must be able to generate multiple independent Knowledge Graph for RAG for diffirent users this...

Ashes47