search

danny-avila / LibreChat

Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. Actively in public development.
https://librechat.ai/
MIT License
17.95k stars 2.99k forks source link

.pptx Support - getting Error processing file #3108

Closed nbhadauria closed 2 months ago

nbhadauria commented 3 months ago

If we have any way to fix this issue or pass the ppt directly to endpoint?

Discussed in https://github.com/danny-avila/LibreChat/discussions/3049

Originally posted by **nbhadauria** June 13, 2024 I am unable to upload a .pptx presentation file while interacting with OpenAI. It looks to be working fine with images and pdf but there is some error with pptx. I am using these version of the docker images. REPOSITORY CREATED SIZE ghcr.io/danny-avila/librechat-dev:latest (2 days ago) 680MB ghcr.io/danny-avila/librechat-rag-api-dev:latest (3 weeks ago) 7.18GB I tried with both ghcr.io/danny-avila/librechat-rag-api-dev-lite **LibraChat error** 2024-06-13 02:00:43 error: Error embedding file Request failed with status code 400 2024-06-13 02:00:43 error: [/files] Error processing file: Request failed with status code 400 **rag_api error (Debug)** 2024-06-13 01:39:16,298 - root - INFO - Request POST http://rag_api:8000/embed - 400 2024-06-13 02:00:18,257 - root - DEBUG - /embed - {'id': '6584018991161084f8b68c59', 'username': 'nitin', 'provider': 'openid', 'email': 'nitinb@.com', 'iat': 1718244016, 'exp': 1718244916} 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_part_begin with no data 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_header_field with data[54:73] 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_header_value with data[75:100] 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_header_end with no data 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_headers_finished with no data 2024-06-13 02:00:18,260 - multipart.multipart - DEBUG - Calling on_part_data with data[104:140] 2024-06-13 02:00:18,261 - multipart.multipart - DEBUG - Calling on_part_end with no data 2024-06-13 02:00:18,261 - multipart.multipart - DEBUG - Calling on_part_begin with no data 2024-06-13 02:00:18,261 - multipart.multipart - DEBUG - Calling on_header_field with data[196:215] 2024-06-13 02:00:18,262 - multipart.multipart - DEBUG - Calling on_header_value with data[217:265] 2024-06-13 02:00:18,262 - multipart.multipart - DEBUG - Calling on_header_end with no data 2024-06-13 02:00:18,262 - multipart.multipart - DEBUG - Calling on_header_field with data[267:279] 2024-06-13 02:00:18,263 - multipart.multipart - DEBUG - Calling on_header_value with data[281:354] 2024-06-13 02:00:18,264 - multipart.multipart - DEBUG - Calling on_header_end with no data 2024-06-13 02:00:18,265 - multipart.multipart - DEBUG - Calling on_headers_finished with no data 2024-06-13 02:00:18,266 - multipart.multipart - DEBUG - Calling on_part_data with data[358:131430] 2024-06-13 02:00:18,270 - multipart.multipart - DEBUG - Calling on_part_data with data[0:262144] 2024-06-13 02:00:18,274 - multipart.multipart - DEBUG - Calling on_part_data with data[0:262144] 2024-06-13 02:00:18,275 - multipart.multipart - DEBUG - Calling on_part_data with data[0:93247] 2024-06-13 02:00:18,276 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,276 - multipart.multipart - DEBUG - Calling on_part_data with data[93248:205909] 2024-06-13 02:00:18,277 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,277 - multipart.multipart - DEBUG - Calling on_part_data with data[205910:262144] 2024-06-13 02:00:18,278 - multipart.multipart - DEBUG - Calling on_part_data with data[0:2215] 2024-06-13 02:00:18,278 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,280 - multipart.multipart - DEBUG - Calling on_part_data with data[2216:262144] 2024-06-13 02:00:18,283 - multipart.multipart - DEBUG - Calling on_part_data with data[0:116537] 2024-06-13 02:00:18,283 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,283 - multipart.multipart - DEBUG - Calling on_part_data with data[116538:146160] 2024-06-13 02:00:18,283 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,284 - multipart.multipart - DEBUG - Calling on_part_data with data[146161:201469] 2024-06-13 02:00:18,284 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,284 - multipart.multipart - DEBUG - Calling on_part_data with data[201470:238392] 2024-06-13 02:00:18,285 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,285 - multipart.multipart - DEBUG - Calling on_part_data with data[238393:262144] 2024-06-13 02:00:18,290 - multipart.multipart - DEBUG - Calling on_part_data with data[0:262144] 2024-06-13 02:00:18,292 - multipart.multipart - DEBUG - Calling on_part_data with data[0:134142] 2024-06-13 02:00:18,292 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,293 - multipart.multipart - DEBUG - Calling on_part_data with data[134143:262144] 2024-06-13 02:00:18,296 - multipart.multipart - DEBUG - Calling on_part_data with data[0:210071] 2024-06-13 02:00:18,296 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,296 - multipart.multipart - DEBUG - Calling on_part_data with data[210072:245201] 2024-06-13 02:00:18,297 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,297 - multipart.multipart - DEBUG - Calling on_part_data with data[245202:262144] 2024-06-13 02:00:18,301 - multipart.multipart - DEBUG - Calling on_part_data with data[0:262100] 2024-06-13 02:00:18,301 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,301 - multipart.multipart - DEBUG - Calling on_part_data with data[262101:262144] 2024-06-13 02:00:18,304 - multipart.multipart - DEBUG - Calling on_part_data with data[0:262132] 2024-06-13 02:00:18,304 - multipart.multipart - DEBUG - Calling on_part_data with data[0:1] 2024-06-13 02:00:18,304 - multipart.multipart - DEBUG - Calling on_part_data with data[262133:262144] 2024-06-13 02:00:18,306 - multipart.multipart - DEBUG - Calling on_part_data with data[0:85632] 2024-06-13 02:00:18,306 - multipart.multipart - DEBUG - Calling on_part_end with no data 2024-06-13 02:00:18,307 - multipart.multipart - DEBUG - Calling on_end with no data 2024-06-13 02:00:20,910 - chardet.charsetprober - DEBUG - SHIFT_JIS Japanese prober hit error at byte 19 2024-06-13 02:00:20,910 - chardet.charsetprober - DEBUG - EUC-JP Japanese prober hit error at byte 14 2024-06-13 02:00:20,911 - chardet.charsetprober - DEBUG - GB2312 Chinese prober hit error at byte 19 2024-06-13 02:00:20,911 - chardet.charsetprober - DEBUG - EUC-KR Korean prober hit error at byte 14 2024-06-13 02:00:20,911 - chardet.charsetprober - DEBUG - CP949 Korean prober hit error at byte 19 2024-06-13 02:00:20,912 - chardet.charsetprober - DEBUG - Big5 Chinese prober hit error at byte 14 2024-06-13 02:00:20,912 - chardet.charsetprober - DEBUG - EUC-TW Taiwan prober hit error at byte 14 2024-06-13 02:00:20,912 - chardet.charsetprober - DEBUG - Johab Korean prober hit error at byte 19 2024-06-13 02:00:43,568 - chardet.charsetprober - DEBUG - windows-1251 Russian confidence = 0.0519902691036774 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - KOI8-R Russian confidence = 0.05259742344161915 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - ISO-8859-5 Russian confidence = 0.05227818947684645 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - MacCyrillic Russian confidence = 0.05205031714201054 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - IBM866 Russian confidence = 0.0528326264751553 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - IBM855 Russian confidence = 0.052263524869906035 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - ISO-8859-7 Greek confidence = 0.08554187950427086 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - windows-1253 Greek confidence = 0.08721162766880206 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - ISO-8859-5 Bulgarian confidence = 0.05145497213310537 2024-06-13 02:00:43,569 - chardet.charsetprober - DEBUG - windows-1251 Bulgarian confidence = 0.05117744056964643 2024-06-13 02:00:43,570 - chardet.charsetprober - DEBUG - TIS-620 Thai confidence = 0.05564437837070073 2024-06-13 02:00:43,570 - chardet.charsetprober - DEBUG - ISO-8859-9 Turkish confidence = 0.06069502635451687 2024-06-13 02:00:43,570 - chardet.charsetprober - DEBUG - ISO-8859-8 Hebrew confidence = 0.0 2024-06-13 02:00:43,570 - chardet.charsetprober - DEBUG - ISO-8859-8 Hebrew confidence = 0.05279139259138128 2024-06-13 02:00:43,570 - chardet.charsetprober - DEBUG - ISO-8859-8 Hebrew confidence = 0.052734155181825414 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - no probers hit minimum threshold 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - utf-8 confidence = 0.010000000000000009 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - SHIFT_JIS Japanese confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - EUC-JP Japanese confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - GB2312 Chinese confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - EUC-KR Korean confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - CP949 Korean confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - Big5 Chinese confidence = 0.01 2024-06-13 02:00:43,570 - chardet.universaldetector - DEBUG - EUC-TW Taiwan confidence = 0.01 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - Johab Korean confidence = 0.01 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - windows-1251 Russian confidence = 0.0519902691036774 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - KOI8-R Russian confidence = 0.05259742344161915 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-5 Russian confidence = 0.05227818947684645 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - MacCyrillic Russian confidence = 0.05205031714201054 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - IBM866 Russian confidence = 0.0528326264751553 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - IBM855 Russian confidence = 0.052263524869906035 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-7 Greek confidence = 0.08554187950427086 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - windows-1253 Greek confidence = 0.08721162766880206 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-5 Bulgarian confidence = 0.05145497213310537 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - windows-1251 Bulgarian confidence = 0.05117744056964643 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - TIS-620 Thai confidence = 0.05564437837070073 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-9 Turkish confidence = 0.06069502635451687 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-8 Hebrew confidence = 0.0 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-8 Hebrew confidence = 0.05279139259138128 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-8 Hebrew confidence = 0.052734155181825414 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - ISO-8859-1 confidence = 0.01 2024-06-13 02:00:43,571 - chardet.universaldetector - DEBUG - MacRoman confidence = 0.0 2024-06-13 02:00:43,574 - root - INFO - Request POST http://rag_api:8000/embed - 400
ervet commented 3 months ago

Hello,

i have the same error. pls see here ... https://github.com/danny-avila/LibreChat/discussions/2462

Never got it to work .. Working only with Azure OpenAI

Greetings Erik

djuillard commented 3 months ago

same for me. I am using Azure OpenAI.

nbhadauria commented 2 months ago

Any update on this issue?

danny-avila commented 2 months ago

Should be solved with this PR: https://github.com/danny-avila/rag_api/pull/62

https://github.com/danny-avila/rag_api/commit/10084b65635136d53f90f268b893545a91cada95