VideoRAG icon indicating copy to clipboard operation
VideoRAG copied to clipboard
Published 3 weeks ago • verified publisher icon HKUDS

Quick Start can not work

Open vron8632 opened this issue 9 months ago • 4 comments

When follow the exmaple to ask questions about the videos! there is a error:

INFO:nano-graphrag:Load KV video_path with 0 data INFO:nano-graphrag:Load KV video_segments with 0 data INFO:nano-graphrag:Load KV text_chunks with 0 data INFO:nano-graphrag:Load KV llm_response_cache with 0 data INFO:nano-vectordb:Init {'embedding_dim': 1536, 'metric': 'cosine', 'storage_file': './videorag-workdir\vdb_entities.json'} 0 data INFO:nano-vectordb:Init {'embedding_dim': 1536, 'metric': 'cosine', 'storage_file': './videorag-workdir\vdb_chunks.json'} 0 data INFO:nano-vectordb:Init {'embedding_dim': 1024, 'metric': 'cosine', 'storage_file': './videorag-workdir\vdb_video_segment_feature.json'} 0 data INFO:transformers_modules.MiniCPM-V-2_6-int4.configuration_minicpm:vision_config is None, using default vision config Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. INFO:openai._base_client:Retrying request to /embeddings in 0.496831 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.751075 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.396852 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.857678 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.430649 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.993724 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.455960 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.949595 seconds INFO:openai._base_client:Retrying request to /embeddings in 0.496733 seconds INFO:openai.base_client:Retrying request to /embeddings in 0.812199 seconds Traceback (most recent call last): File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity\asyncio_init.py", line 114, in call result = await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_llm.py", line 148, in openai_embedding response = await openai_async_client.embeddings.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai\resources\embeddings.py", line 243, in create return await self._post( ^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1767, in post return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1461, in request return await self._request( ^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1547, in _request return await self._retry_request( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1594, in _retry_request return await self._request( ^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1547, in _request return await self._retry_request( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1594, in _retry_request return await self._request( ^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\openai_base_client.py", line 1562, in _request raise self._make_status_error_from_response(err.response) from None openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "D:\Projects\027_mllm\VideoRAG-long\start02_ask.py", line 34, in response = videorag.query(query=query, param=param) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag\videorag.py", line 304, in query return loop.run_until_complete(self.aquery(query, param)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\asyncio\base_events.py", line 654, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag\videorag.py", line 308, in aquery response = await videorag_query( ^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_op.py", line 598, in videorag_query results = await chunks_vdb.query(query, top_k=query_param.top_k) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_storage\vdb_nanovectordb.py", line 59, in query embedding = await self.embedding_func([query]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_utils.py", line 190, in wait_func result = await func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_utils.py", line 173, in call return await self.func(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Projects\027_mllm\VideoRAG-long\videorag_utils.py", line 173, in call return await self.func(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity\asyncio_init_.py", line 189, in async_wrapped return await copy(fn, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity\asyncio_init_.py", line 111, in call do = await self.iter(retry_state=retry_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity\asyncio_init_.py", line 153, in iter result = await action(retry_state) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity_utils.py", line 99, in inner return call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\ProgramData\miniconda3\envs\videorag\Lib\site-packages\tenacity_init_.py", line 421, in exc_check raise retry_exc from fut.exception() tenacity.RetryError: RetryError[<Future at 0x1cb2e0c6990 state=finished raised RateLimitError>]

vron8632 avatar Apr 13 '25 01:04 vron8632

Thank you for your interest in our work!

The error message indicates: openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

You may want to check whether your OpenAI API key has sufficient funds or an active plan to access the service normally.

xlrrrr avatar Apr 13 '25 02:04 xlrrrr

Thank you for your interest in our work!

The error message indicates: openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

You may want to check whether your OpenAI API key has sufficient funds or an active plan to access the service normally.

Can I use my local model,I can not find how to modify the url.

sherlockma11 avatar Apr 14 '25 08:04 sherlockma11

Thank you for your interest in our work!

The error message indicates: openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

You may want to check whether your OpenAI API key has sufficient funds or an active plan to access the service normally.

Thank you for your answer, one more question, how can I use the local model such as Qwen2.5-VL instead of OpenAI API service?

vron8632 avatar Apr 15 '25 09:04 vron8632

Thank you for your interest in our work! The error message indicates: openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}} You may want to check whether your OpenAI API key has sufficient funds or an active plan to access the service normally.

Thank you for your answer, one more question, how can I use the local model such as Qwen2.5-VL instead of OpenAI API service?

Hi, @vron8632 , has this problem solved?

Shengnan-Zhu avatar Jan 07 '26 12:01 Shengnan-Zhu