[Bug]: File upload not working

[abdullah-w-21]

What happened?

File upload feature is not working for text, word, pdf files however we can upload information

Version Information

version=1.1.5

Steps to Reproduce

Just try to upload a word or pdf file

What browsers are you seeing the problem on?

Chrome

Relevant log output

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[rubentalstra]

@abdullah-w-21 are you running RAG_API? if not then it won't work you need to have a RAG running on the backend.

https://www.librechat.ai/docs/features/rag_api

[abdullah-w-21]

@abdullah-w-21 are you running RAG_API? if not then it won't work you need to have a RAG running on the backend.

https://www.librechat.ai/docs/features/rag_api

Yeah I tried to configure the RAG api and used openai's embedding but still it was the same output, I guess I am doing something wrong in the configuration

[rubentalstra]

did you setup in the .env file the connection string to the RAG?

[abdullah-w-21]

did you setup in the .env file the connection string to the RAG?

Yeah I did that but let me try again, it could be a problem on my side only. I guess before this update it was working fine.

[rubentalstra]

the RAG needs to be running and after that LibreChat. it only connects during startup.

[abdullah-w-21]

Yeah i use the deploy compose so it does that automatically right?

[Wicaeed]

I'm running into a similar issue, I've set my config options:
I've tried host.docker.internal, 127.0.0.1 and the below, and all start the API just fine in the logs, but all error with the same error as well:

RAG_OPENAI_BASEURL=http://rag_api:8000 <--- know this is not in documentation but this is guaranteed to work thx to Docker Compose networking
RAG_OPENAI_API_KEY=sk-proj-<key>
# RAG_USE_FULL_CONTEXT=
EMBEDDINGS_PROVIDER=openai
EMBEDDINGS_MODEL=text-embedding-3-small

It starts fine, I ran a test convo to ChatGPT fine, and then attempted to attach a 3Kb CSV to the convo and it gets an error in the UI:

2025-03-15T05:07:03.184Z debug: No unwanted Token indexes found.
2025-03-15T05:07:03.238Z debug: [indexSync] There are 14 messages and 14 indexed
2025-03-15T05:07:03.238Z debug: [indexSync] There are 1 convos and 1 indexed
2025-03-15T05:07:03.260Z error: Config file YAML format is invalid: ENOENT: no such file or directory, open '/app/librechat.yaml'
2025-03-15T05:07:03.261Z warn: Default value for CREDS_KEY is being used.
2025-03-15T05:07:03.261Z warn: Default value for CREDS_IV is being used.
2025-03-15T05:07:03.261Z warn: Default value for JWT_SECRET is being used.
2025-03-15T05:07:03.262Z warn: Default value for JWT_REFRESH_SECRET is being used.
2025-03-15T05:07:03.262Z info: Please replace any default secret values.
2025-03-15T05:07:03.262Z info: ​

    For your convenience, use this tool to generate your own secret values:
    https://www.librechat.ai/toolkit/creds_generator

    ​
2025-03-15T05:07:03.473Z info: RAG API is running and reachable at http://rag_api:8000.
2025-03-15T05:07:03.487Z info: No changes needed for 'USER' role permissions
2025-03-15T05:07:03.489Z info: No changes needed for 'ADMIN' role permissions
2025-03-15T05:07:03.496Z info: Server listening on all interfaces at port 3080. Use http://localhost:3080 to access it
2025-03-15T05:07:06.586Z debug: [validateJson] files
["\"Ai_PDF.json\"","\"BrowserOp.json\"","\"Dr_Thoths_Tarot.json\"","\"DreamInterpreter.json\"","\"VoxScript.json\"","\"askyourpdf.json\"","\"drink_maestro.json\"","\"earthImagesAndVisualizations.json\"","\"image_prompt_enhancer.json\"","\"qrCodes.json\"","\"scholarai.json\"","\"uberchord.json\"","\"web_search.json\""]
2025-03-15T05:09:09.103Z debug: [AskController]
{
  text: "Hello generate me a test response please",
  conversationId: null,
  endpoint: "openAI",
  resendFiles: true,
    modelOptions.model: "gpt-4o-2024-11-20",
  modelsConfig: "exists",
}
2025-03-15T05:09:09.214Z debug: [BaseClient] Loading history:
{
  conversationId: "8efbd973-9029-4c0c-bf6d-7af156eda0a8",
  parentMessageId: "00000000-0000-0000-0000-000000000000",
}
2025-03-15T05:09:09.349Z debug: [BaseClient] Context Count (1/2)
{
  remainingContextTokens: 127486,
  maxContextTokens: 127500,
}
2025-03-15T05:09:09.349Z debug: [BaseClient] Context Count (2/2)
{
  remainingContextTokens: 127486,
  maxContextTokens: 127500,
}
2025-03-15T05:09:09.349Z debug: [BaseClient] tokenCountMap:
{
  7b188373-7b5e-4d6d-9c64-ea4a781f0e24: 11,
}
2025-03-15T05:09:09.350Z debug: [BaseClient]
{
  promptTokens: 14,
  remainingContextTokens: 127486,
  payloadSize: 1,
  maxContextTokens: 127500,
}
2025-03-15T05:09:09.350Z debug: [BaseClient] tokenCountMap
{
  7b188373-7b5e-4d6d-9c64-ea4a781f0e24: 11,
  instructions: undefined,
}
2025-03-15T05:09:09.350Z debug: [BaseClient] userMessage
{
  messageId: "7b188373-7b5e-4d6d-9c64-ea4a781f0e24",
  parentMessageId: "00000000-0000-0000-0000-000000000000",
  conversationId: "8efbd973-9029-4c0c-bf6d-7af156eda0a8",
  sender: "User",
  text: "Hello generate me a test response please",
  isCreatedByUser: true,
  tokenCount: 11,
}
2025-03-15T05:09:09.352Z debug: [OpenAIClient] chatCompletion
{
  baseURL: "https://api.openai.com/v1",
    modelOptions.model: "gpt-4o-2024-11-20",
    modelOptions.user: "67d50102be6fd0a154b5b495",
    modelOptions.stream: true,
    // 1 message(s)
    modelOptions.messages: [{"role":"user","content":"Hello generate me a test response please"}],
}
2025-03-15T05:09:09.361Z debug: Making request to https://api.openai.com/v1/chat/completions
2025-03-15T05:09:09.378Z debug: [saveConvo] api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo
2025-03-15T05:09:10.793Z debug: [OpenAIClient] chatCompletion response
{
  object: "chat.completion",
  service_tier: "default",
    usage.prompt_tokens: 14,
    usage.completion_tokens: 49,
    usage.total_tokens: 63,
    prompt_tokens_details.cached_tokens: 0,
    prompt_tokens_details.audio_tokens: 0,
    completion_tokens_details.reasoning_tokens: 0,
    completion_tokens_details.audio_tokens: 0,
    completion_tokens_details.accepted_prediction_tokens: 0,
    completion_tokens_details.rejected_prediction_tokens: 0,
  id: "chatcmpl-BBE3iMltIH5l83774tMB2KBflSMkM",
  // 1 choice(s)
  choices: [{"message":{"role":"assistant","content":"Hello! Sure thing — here's a test response just for you:\n... [truncated]],
  created: 1742015350,
  model: "gpt-4o-2024-11-20",
  system_fingerprint: "fp_1d7c5f52ce",
}
2025-03-15T05:09:10.797Z debug: [spendTokens] conversationId: 8efbd973-9029-4c0c-bf6d-7af156eda0a8 | Context: message | Token usage:
{
  promptTokens: 14,
  completionTokens: 49,
}
2025-03-15T05:09:10.821Z debug: [spendTokens] No transactions incurred against balance
2025-03-15T05:09:10.821Z debug: [spendTokens] conversationId: 8efbd973-9029-4c0c-bf6d-7af156eda0a8 | Context: reasoning | Token usage:
{
  promptTokens: undefined,
  completionTokens: 0,
}
2025-03-15T05:09:10.823Z debug: [spendTokens] No transactions incurred against balance
2025-03-15T05:09:10.829Z debug: [saveConvo] api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo
2025-03-15T05:09:10.838Z debug: [AskController] Request closed
2025-03-15T05:09:10.848Z debug: [createStartHandler] handleChatModelStart: title
{
  model: "gpt-4o-mini",
    function_call.name: "output_formatter",
}
2025-03-15T05:09:11.100Z debug: [createStartHandler]
{
  prelimPromptTokens: 91,
  tokenBuffer: 150,
}
2025-03-15T05:09:11.575Z debug: [RunManager] handleLLMEnd: {"context":"title","tokenBuffer":150,"conversationId":"8efbd973-9029-4c0c-bf6d-7af156eda0a8"}
{
  runId: "11aedace-d735-4634-b4ef-e7e4ad9a51e1",
  _parentRunId: undefined,
    tokenUsage.promptTokens: 92,
    tokenUsage.completionTokens: 6,
    tokenUsage.totalTokens: 98,
}
2025-03-15T05:09:11.576Z debug: [spendTokens] conversationId: 8efbd973-9029-4c0c-bf6d-7af156eda0a8 | Context: title | Token usage:
{
  promptTokens: 92,
  completionTokens: 6,
}
2025-03-15T05:09:11.581Z debug: [spendTokens] No transactions incurred against balance
2025-03-15T05:09:11.581Z debug: [createStartHandler] handleChatModelStart: title
{
  model: "gpt-4o-mini",
    function_call.name: "output_formatter",
}
2025-03-15T05:09:11.583Z debug: [createStartHandler]
{
  prelimPromptTokens: 189,
  tokenBuffer: 150,
}
2025-03-15T05:09:12.098Z debug: [RunManager] handleLLMEnd: {"context":"title","tokenBuffer":150,"conversationId":"8efbd973-9029-4c0c-bf6d-7af156eda0a8"}
{
  runId: "747fec93-d6e3-4d0b-8cce-b5dbb86483ef",
  _parentRunId: undefined,
    tokenUsage.promptTokens: 189,
    tokenUsage.completionTokens: 9,
    tokenUsage.totalTokens: 198,
}
2025-03-15T05:09:12.098Z debug: [spendTokens] conversationId: 8efbd973-9029-4c0c-bf6d-7af156eda0a8 | Context: title | Token usage:
{
  promptTokens: 189,
  completionTokens: 9,
}
2025-03-15T05:09:12.099Z debug: [OpenAIClient] Convo Title: Test Response Generation Request
2025-03-15T05:09:12.099Z debug: [saveConvo] api/server/services/Endpoints/openAI/addTitle.js
2025-03-15T05:09:12.104Z debug: [spendTokens] No transactions incurred against balance
-----Attempt to attach a CSV from the UI in Chrome-------
2025-03-15T05:09:28.366Z debug: Error code: 401 - {'detail': 'Invalid token: Not enough segments'}
{
  status: false,
  file_id: "90fefc7a-7ed0-4a68-b797-adb4008bb293",
  filename: "History_for_Account_X85917968.csv",
  known_type: true,
}
2025-03-15T05:09:28.367Z error: Error uploading vectors An error occurred while setting up the request: File embedding failed.
2025-03-15T05:09:28.367Z error: [/files] Error processing file: File embedding failed.

[abdullah-w-21]

I faced the same problem it was not written in their docs however I solved mine this is what i added in my env this worked for me it should work for you as well:

RAG_OPENAI_API_KEY=sk-
RAG_PORT=8000

RAG_USE_FULL_CONTEXT=

EMBEDDINGS_PROVIDER=openai
EMBEDDINGS_MODEL=text-embedding-3-small