[Bug]: knowledge graph not working, error NO API on aliyuncs,com

boaty commented 3 weeks ago

Is there an existing issue for the same bug?

[X] I have checked the existing issues.

Branch name

knowledgebase chunk method knowledge graph

Commit ID

2024-08-22

Other environment information

ubuntu 22
GTX 3080

Actual behavior

I got error while building database of knowledge graph type.

error message is related to NO API key for aliyuncs.com

i tried different embedding methods and minitor the docker logs, i found the error occurred after embedding part is done. So bug must be in chunk method

Expected behavior

knowledge graph built and we can see it in dataset by clicking the file name.

Steps to reproduce

1.upload a english scientific article in pdf
2.in configuration, selected chunk method as knowledge graph
3.enter entity type. (in my case, is bacteria, disease and relationship)
4. run 'UNSTRAT' in dataset for the uploaded article

Additional information

[ERROR] [2024-08-22 07:16:53,692] [http_request._handle_response] [line:172]: Request: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation failed, status: 401, message: Invalid API-key provided. [ERROR] [2024-08-22 07:16:54,744] [http_request._handle_response] [line:172]: Request: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation failed, status: 401, message: Invalid API-key provided. [ERROR] [2024-08-22 07:16:55,454] [http_request._handle_response] [line:172]: Request: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation failed, status: 401, message: Invalid API-key provided. [ERROR] [2024-08-22 07:16:56,271] [http_request._handle_response] [line:172]: Request: https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding failed, status: 401, message: Invalid API-key provided. /ragflow/rag/utils/es_conn.py:131: ElasticsearchWarning: A bulk action object contained multiple keys. Additional keys are currently ignored but will be rejected in a future version. r = self.es.bulk(index=(self.idxnm if not idx_nm else

KevinHuSh commented 2 weeks ago

You need to set API-key for your choosen LLM supplier.

cassiusoat commented 2 weeks ago

I have a similar issue, and I confirm API-key has been set for aliyun. However, the graph could not be established because of "Request timed out"

Additional information

[INFO] [2024-08-25 11:54:03,688] [_internal._log] [line:96]: 172.18.0.5 - - [25/Aug/2024 11:54:03] "GET /v1/document/list?kb_id=71a4f66e622211efa8320242ac120006&page=1&page_size=10 HTTP/1.1" 200 - [ERROR] [2024-08-25 11:54:10,550] [http_request._handle_response] [line:172]: Request: https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation failed, status: 500, message: Request timed out, please try again later. Traceback (most recent call last): File "/ragflow/graphrag/graph_extractor.py", line 139, in call result, token_count = self._process_document(text, prompt_variables) File "/ragflow/graphrag/graph_extractor.py", line 188, in _process_document if response.find("ERROR") >=0: raise Exception(response) Exception: ERROR: Request timed out, please try again later.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/ragflow/rag/svr/task_executor.py", line 165, in build cks = chunker.chunk(row["name"], binary=binary, from_page=row["from_page"], File "/ragflow/rag/app/knowledge_graph.py", line 18, in chunk chunks = build_knowlege_graph_chunks(tenant_id, sections, callback, File "/ragflow/graphrag/index.py", line 85, in build_knowlege_graphchunks graphs.append(.result().output) File "/usr/lib/python3.10/concurrent/futures/_base.py", line 458, in result return self.get_result() File "/usr/lib/python3.10/concurrent/futures/_base.py", line 403, in get_result raise self._exception File "/usr/lib/python3.10/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) File "/ragflow/graphrag/graph_extractor.py", line 145, in call if callback: callback("Knowledge graph extraction error:{}".format(str(e))) File "/ragflow/rag/svr/task_executor.py", line 80, in set_progress if prog is not None and prog < 0: TypeError: '<' not supported between instances of 'str' and 'int'

jarodttt commented 1 week ago

I changed the "system model settings" and it works:

top right corner-your icon, choose "Model Provider" from left check "system Model settings" Change the "Embedding model"- this is the key step

infiniflow / ragflow