File upload impossible since update

[samuelhalff]

What happened?

"Chat with files" was working fine until I updated to latest release.
I had embeddings setup in .env via azure.
As long as the file was OCR, its content would be part of the conversation context.

Since the update, I cannot get the "upload file" or "upload as text" button to appear.

I setup a Mistral OCR as per documation in librechat.yaml, and tried pretty much all settings I found here and elsewhere, but my UI only allows the upload of images.

What is it I am doing wrong, any obvious clue as to what is missing?

I have no error in my logs, RAG seems to be working as far I as I see.. Drag and dropping a pdf in the UI throws an error about capabilities not being enabled but I don't see where to set this.

Thanks for any advice here.

Version Information

ghcr.io/danny-avila/librechat-dev latest 01f82e6dbabb 46 hours ago 1.11GB
ghcr.io/danny-avila/librechat-rag-api-dev-lite latest 6a1dfa1c7fe0 11 days ago 1.47GB

Steps to Reproduce

Setup azure RAG in .env:

#RAG_OPENAI_BASEURL=https://pbmch8303697696.openai.azure.com/
RAG_AZURE_OPENAI_ENDPOINT=https://pbmch8303697696.cognitiveservices.azure.com
#RAG_OPENAI_API_KEY=REDACTED
RAG_AZURE_OPENAI_API_KEY=REDACTED
RAG_AZURE_OPENAI_VERSION=2024-12-01-preview
OPENAI_API_VERSION=2024-12-01-preview

RAG_USE_FULL_CONTEXT=

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

Setup OCR in librechat.yaml:

OCR Config

ocr:
mistralModel: "mistral-small-2503"
apiKey: "REDACTED"
baseURL: "https://REDACTED.services.ai.azure.com/models/"
strategy: "azure_mistral_ocr"

What browsers are you seeing the problem on?

Chrome

Relevant log output

No error or other debug logs that are useful regarding the issue

Screenshots

No response

Code of Conduct

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

[danny-avila]

Mind sharing screenshots and an example librechat.yaml config? It should be more than possible (on latest commit):

---

Examples

[danny-avila]

It's likely the librechat.yaml config has an error.

Log locations:

• Docker: Project root directory ./logs
• npm: ./api/logs

There are two types of logs that can help diagnose the issue:

• debug logs (debug-YYYY-MM-DD.log)
• error logs (error-YYYY-MM-DD.log)

Error logs contain exact stack traces and are especially helpful, but both can provide valuable information.

[samuelhalff]

This is my (redacted) full librechat.yaml:

# For more information, see the Configuration Guide:
# https://www.librechat.ai/docs/configuration/librechat_yaml

# Configuration version (required)
version: 1.2.1

# Cache settings: Set to true to enable caching
cache: true

# Custom interface configuration
interface:
  customWelcome: "Welcome to PBM AI. Enjoy your experience."
  # Privacy policy settings
  privacyPolicy:
    externalUrl: 'https://librechat.ai/privacy-policy'
    openNewTab: true

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true
    modalAcceptance: true
    modalTitle: "Terms of Service for LibreChat"
    modalContent: |
      # Terms and Conditions for LibreChat

      *Effective Date: February 18, 2024*

      Welcome to LibreChat, the informational website for the open-source AI chat platform, available at https://librechat.ai. These Terms of Service ("Terms") govern your use of our website and the services we offer. By accessing or using the Website, you agree to be bound by these Terms and our Privacy Policy, accessible at https://librechat.ai//privacy.

      ## 1. Ownership

      Upon purchasing a package from LibreChat, you are granted the right to download and use the code for accessing an admin panel for LibreChat. While you own the downloaded code, you are expressly prohibited from reselling, redistributing, or otherwise transferring the code to third parties without explicit permission from LibreChat.

      ## 2. User Data

      We collect personal data, such as your name, email address, and payment information, as described in our Privacy Policy. This information is collected to provide and improve our services, process transactions, and communicate with you.

      ## 3. Non-Personal Data Collection

      The Website uses cookies to enhance user experience, analyze site usage, and facilitate certain functionalities. By using the Website, you consent to the use of cookies in accordance with our Privacy Policy.

      ## 4. Use of the Website

      You agree to use the Website only for lawful purposes and in a manner that does not infringe the rights of, restrict, or inhibit anyone else's use and enjoyment of the Website. Prohibited behavior includes harassing or causing distress or inconvenience to any person, transmitting obscene or offensive content, or disrupting the normal flow of dialogue within the Website.

      ## 5. Governing Law

      These Terms shall be governed by and construed in accordance with the laws of the United States, without giving effect to any principles of conflicts of law.

      ## 6. Changes to the Terms

      We reserve the right to modify these Terms at any time. We will notify users of any changes by email. Your continued use of the Website after such changes have been notified will constitute your consent to such changes.

      ## 7. Contact Information

      If you have any questions about these Terms, please contact us at [REDACTED_EMAIL].

      By using the Website, you acknowledge that you have read these Terms of Service and agree to be bound by them.

  endpointsMenu: true
  modelSelect: true
  parameters: true
  sidePanel: true
  presets: true
  prompts: true
  bookmarks: true
  multiConvo: true
  agents: true

# Example Registration Object Structure (optional)
registration:
  #socialLogins: ['github', 'google', 'discord', 'openid', 'facebook', 'apple']
  allowedDomains:
    - "[REDACTED_DOMAIN_1]"
    - "[REDACTED_DOMAIN_2]"
    - "[REDACTED_DOMAIN_3]"

speech:
#   tts:
#     openai:
#       url: ''
#       apiKey: '${TTS_API_KEY}'
#       model: ''
#       voices: ['']

#
  stt:
    azureOpenAI:
      instanceName: '[REDACTED_INSTANCE_NAME]'
      deploymentName: 'whisper'
      #url: '[REDACTED_URL]'
      apiKey: '[REDACTED_API_KEY]'
      #model: 'whisper'
      apiVersion: '2024-06-01'
  speechTab:
    advancedMode: true
    speechToText:
      engineSTT: "external"
      languageSTT: "French"
      autoTranscribeAudio: true
      decibelValue: -45
      autoSendText: -1

# rateLimits:
#   fileUploads:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for file uploads per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for file uploads per user
#   conversationsImport:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for conversation imports per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for conversation imports per user

# Example Actions Object Structure
actions:
  allowedDomains:
    - "swapi.dev"
    - "librechat.ai"
    - "google.com"

# OCR Config
ocr:
  mistralModel: "mistral-small-2503"
  apiKey: "[REDACTED_API_KEY]"
  baseURL: "[REDACTED_URL]"
  strategy: "azure_mistral_ocr"

# Example MCP Servers Object Structure
# mcpServers:
#   everything:
#     # type: sse # type can optionally be omitted
#     url: http://localhost:3001/sse
#     timeout: 60000  # 1 minute timeout for this server, this is the default timeout for MCP servers.
#   puppeteer:
#     type: stdio
#     command: npx
#     args:
#       - -y
#       - "@modelcontextprotocol/server-puppeteer"
#     timeout: 300000  # 5 minutes timeout for this server
#   filesystem:
#     # type: stdio
#     command: npx
#     args:
#       - -y
#       - "@modelcontextprotocol/server-filesystem"
#       - /home/user/LibreChat/
#     iconPath: /home/user/LibreChat/client/public/assets/logo.svg
#  mcp-obsidian:
#    command: npx
#    args:
#      - -y
#      - "mcp-obsidian"
#      - /path/to/obsidian/vault

balance:
  enabled: false

# Definition of custom endpoints
endpoints:
  assistants:
    disableBuilder: false # Disable Assistants Builder Interface by setting to `true`
    #...
    retrievalModels: ["gpt-4.1", "o3-mini"]
    capabilities: ["code_interpreter", "retrieval", "actions", "tools", "image_vision"]
  agents:
    disableBuilder: false
    capabilities: ["execute_code", "file_search", "actions", "ocr", "tools"]
  azureOpenAI:
    titleModel: "gpt-4.1"
    titleConvo: true
    titleMethod: "completion"
    plugins: false
    assistants: true
    groups:
    - group: "new-api"
      assistants: true
      apiKey: "[REDACTED_API_KEY]"
#      baseURL: "[REDACTED_URL]"
      version: "2025-01-01-preview"
      instanceName: "[REDACTED_INSTANCE_NAME]"
#     serverless: true
      capabilities: ["execute_code", "file_search", "actions", "ocr", "tools"]
      models:
        gpt-4.1:
          deploymentName: " gpt-4.1"
        o3-mini:
          deploymentName: "o3-mini"
        DeepSeek-R1-0528:
          deploymentName: "DeepSeek-R1-0528"

  azureAssistants:
    capabilities: ["code_interpreter", "actions", "tools", "image_vision", "retrieval"]
    disableBuilder: false # Disable Assistants Builder Interface by setting to true

  # custom example endpoints are commented out

fileConfig:
  endpoints:
    agents:
      fileLimit: 5
      fileSizeLimit: 100  # Maximum size for an individual file in MB
      totalSizeLimit: 500  # Maximum total size for all files in a single request in MB
      supportedMimeTypes:
        - "image/.*"
        - "text/plain"
        - "text/markdown"
        - "text/csv"
        - "application/pdf"
        - "application/json"
        - "application/msword"
        - "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    assistants:
      fileLimit: 5
      fileSizeLimit: 10  # Maximum size for an individual file in MB
      totalSizeLimit: 50  # Maximum total size for all files in a single request in MB
      supportedMimeTypes:
        - "image/.*"
        - "application/pdf"
    openAI:
      disabled: true  # Disables file uploading to the OpenAI endpoint
    azureOpenAI:
      disabled: false
      fileLimit: 25
      fileSizeLimit: 100
      supportedMimeTypes:
        - "image/.*"
        - "image/png"
        - "image/webp"
        - "image/gif"
        - "text/plain"
        - "text/markdown"
        - "text/csv"
        - "application/pdf"
        - "application/json"
        - "application/msword"
        - "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    default:
      totalSizeLimit: 20
  serverFileSizeLimit: 100  # Global server file size limit in MB
  avatarSizeLimit: 2  # Limit for user avatar image size in MB
# See the Custom Configuration Guide for more information on Assistants Config:
# https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/assistants_endpoint

[danny-avila]

what do your logs look like on app startup?

[samuelhalff]

Attached. Do you see anything helpful ?

…

On Tue, 1 Jul 2025 at 22:25, Danny Avila ***@***.***> wrote: what do your logs look like on app startup? — Reply to this email directly, view it on GitHub <#8172 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFBEXXSA5EOA3LQNOHOTYT3GLVE3AVCNFSM6AAAAACAR6ZC52VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNRTGI4DMNQ> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[danny-avila]

Attached. Do you see anything helpful ?

Only need to see the logs relevant to when you first start the app.

[danny-avila]

also, no screenshots of where you are expecting the upload options have been shared

[samuelhalff]

I don’t see anything relevant here:

2025-07-01T18:47:56.913Z debug: [spendTokens] No transactions incurred against balance
2025-07-01T18:47:56.915Z debug: [saveConvo] api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo
2025-07-01T18:47:56.924Z debug: [AgentController] Request closed
2025-07-01T18:47:56.926Z debug: [AgentController] Performing cleanup
2025-07-01T18:47:56.926Z debug: [AgentController] Cleaning up abort controller
2025-07-01T18:47:56.926Z debug: [AgentController] Cleanup completed
2025-07-01T18:57:27.384Z info: Cleaning up FlowStateManager intervals...
2025-07-01T18:58:59.301Z info: [Optional] Redis not initialized.
2025-07-01T18:59:10.935Z info: [Optional] IoRedis not initialized for rate limiters.
2025-07-01T18:59:12.170Z info: Connected to MongoDB
2025-07-01T18:59:12.171Z info: [indexSync] Starting index synchronization check...
2025-07-01T18:59:12.301Z info: Custom config file loaded:
2025-07-01T18:59:12.306Z debug: Web search serperApiKey: Using environment variable SERPER_API_KEY (not set in environment, user provided value)
2025-07-01T18:59:12.302Z info: {
"version": "1.2.1",
"cache": true,
"interface": {
"customWelcome": "Welcome to
AI. Enjoy your experience.",
"privacyPolicy": {
... [truncated]
2025-07-01T18:59:12.303Z debug: Custom config:
{
version: "1.2.1",
cache: true,
interface.customWelcome: "Welcome to AI. Enjoy your experience.",
privacyPolicy.externalUrl: "https://librechat.ai/privacy-policy",
privacyPolicy.openNewTab: true,
termsOfService.externalUrl: "https://librechat.ai/tos",
termsOfService.openNewTab: true,
termsOfService.modalAcceptance: true,
termsOfService.modalTitle: "Terms of Service for LibreChat",
termsOfService.modalContent: "# Terms and Conditions for LibreChat\n\nEffective Date: February 18, 2024\n\nWelcome to LibreChat, the... [truncated]",
interface.endpointsMenu: true,
interface.modelSelect: true,
interface.parameters: true,
interface.sidePanel: true,
interface.presets: true,
interface.prompts: true,
interface.bookmarks: true,
interface.multiConvo: true,
interface.agents: true,
// 3 allowedDomain….."],
azureOpenAI.instanceName: "….",
azureOpenAI.deploymentName: "whisper",
azureOpenAI.apiKey: "…",
azureOpenAI.apiVersion: "2024-06-01",
speechTab.advancedMode: true,
speechToText.engineSTT: "external",
speechToText.languageSTT: "French",
speechToText.autoTranscribeAudio: true,
speechToText.decibelValue: -45,
speechToText.autoSendText: -1,
// 3 allowedDomain(s)
actions.allowedDomains: ["swapi.dev","librechat.ai","google.com"],
ocr.mistralModel: "mistral-small-2503",
ocr.apiKey: "…",
ocr.baseURL: "https://…...services.ai.azure.com/models/",
ocr.strategy: "azure_mistral_ocr",
balance.enabled: false,
assistants.disableBuilder: false,
agents.disableBuilder: false,
// 5 capabilitie(s)
agents.capabilities: ["execute_code","file_search","actions","ocr","tools"],
azureOpenAI.titleModel: "gpt-4.1",
azureOpenAI.titleConvo: true,
azureOpenAI.titleMethod: "completion",
azureOpenAI.plugins: false,
azureOpenAI.assistants: true,
// 1 group(s)
azureOpenAI.groups: [{"group":"new-api","assistants":true,"apiKey":"... [truncated]],
// 5 capabilitie(s)
azureAssistants.capabilities: ["code_interpreter","actions","tools","image_vision","retrieval"],
azureAssistants.disableBuilder: false,
agents.fileLimit: 5,
agents.fileSizeLimit: 100,
agents.totalSizeLimit: 500,
// 8 supportedMimeType(s)
agents.supportedMimeTypes: ["image/.","text/plain","text/markdown","text/csv","application/pdf","application/json","application/msword","application/vnd.openxmlformats-officedocument.wordprocessingml.document"],
assistants.fileLimit: 5,
assistants.fileSizeLimit: 10,
assistants.totalSizeLimit: 50,
// 2 supportedMimeType(s)
assistants.supportedMimeTypes: ["image/.","application/pdf"],
openAI.disabled: true,
azureOpenAI.disabled: false,
azureOpenAI.fileLimit: 25,
azureOpenAI.fileSizeLimit: 100,
// 11 supportedMimeType(s)
azureOpenAI.supportedMimeTypes: ["image/.*","image/png","image/webp","image/gif","text/plain","text/markdown","text/csv","application/pdf","application/json","application/msword","application/vnd.openxmlformats-officedocument.wordprocessingml.document"],
default.totalSizeLimit: 20,
fileConfig.serverFileSizeLimit: 100,
fileConfig.avatarSizeLimit: 2,
}
2025-07-01T18:59:12.306Z debug: Web search firecrawlApiKey: Using environment variable FIRECRAWL_API_KEY (not set in environment, user provided value)
2025-07-01T18:59:12.307Z debug: Web search firecrawlApiUrl: Using environment variable FIRECRAWL_API_URL (not set in environment, user provided value)
2025-07-01T18:59:12.307Z debug: Web search jinaApiKey: Using environment variable JINA_API_KEY (not set in environment, user provided value)
2025-07-01T18:59:12.307Z debug: Web search cohereApiKey: Using environment variable COHERE_API_KEY (not set in environment, user provided value)
2025-07-01T18:59:12.307Z warn: Default value for CREDS_KEY is being used.
2025-07-01T18:59:12.308Z warn: Default value for CREDS_IV is being used.
2025-07-01T18:59:12.308Z warn: Default value for JWT_SECRET is being used.
2025-07-01T18:59:12.308Z warn: Default value for JWT_REFRESH_SECRET is being used.
2025-07-01T18:59:12.309Z info: Please replace any default secret values.
2025-07-01T18:59:12.309Z info: �

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

�

2025-07-01T18:59:12.309Z warn: The CHECK_BALANCE environment variable is deprecated. Please use the balance field in the librechat.yaml config file instead.
More info: https:/... [truncated]
2025-07-01T18:59:12.425Z debug: [MEILI_SYNC:meili-index-sync] Creating initial flow state
2025-07-01T18:59:12.445Z info: RAG API is running and reachable at http://rag_api:8000.
2025-07-01T18:59:12.517Z info: Migrating 'USER' role from old schema: found 'PROMPTS' at top level
2025-07-01T18:59:12.517Z info: Migrating 'USER' role from old schema: found 'BOOKMARKS' at top level
2025-07-01T18:59:12.518Z info: Migrating 'USER' role from old schema: found 'AGENTS' at top level
2025-07-01T18:59:12.518Z info: Migrating 'USER' role from old schema: found 'MULTI_CONVO' at top level
2025-07-01T18:59:12.518Z info: Migrating 'USER' role from old schema: found 'TEMPORARY_CHAT' at top level
2025-07-01T18:59:12.518Z info: Migrating 'USER' role from old schema: found 'RUN_CODE' at top level
2025-07-01T18:59:12.519Z info: Unsetting old schema fields for 'USER' role: PROMPTS, BOOKMARKS, AGENTS, MULTI_CONVO, TEMPORARY_CHAT, RUN_CODE
2025-07-01T18:59:12.529Z info: Updated role 'USER' and removed old schema fields
2025-07-01T18:59:12.529Z info: Updated 'USER' role permissions
2025-07-01T18:59:12.531Z info: Migrating 'ADMIN' role from old schema: found 'PROMPTS' at top level
2025-07-01T18:59:12.531Z info: Migrating 'ADMIN' role from old schema: found 'BOOKMARKS' at top level
2025-07-01T18:59:12.531Z info: Migrating 'ADMIN' role from old schema: found 'AGENTS' at top level
2025-07-01T18:59:12.531Z info: Migrating 'ADMIN' role from old schema: found 'MULTI_CONVO' at top level
2025-07-01T18:59:12.532Z info: Migrating 'ADMIN' role from old schema: found 'TEMPORARY_CHAT' at top level
2025-07-01T18:59:12.532Z info: Migrating 'ADMIN' role from old schema: found 'RUN_CODE' at top level
2025-07-01T18:59:12.532Z info: Unsetting old schema fields for 'ADMIN' role: PROMPTS, BOOKMARKS, AGENTS, MULTI_CONVO, TEMPORARY_CHAT, RUN_CODE
2025-07-01T18:59:12.537Z info: Updated role 'ADMIN' and removed old schema fields
2025-07-01T18:59:12.538Z info: Turnstile is DISABLED (no siteKey provided).
2025-07-01T18:59:12.537Z info: Updated 'ADMIN' role permissions
2025-07-01T18:59:12.781Z debug: [openidStrategy] Request to: https://login.microsoftonline.com/b81c4237-e300-4913-abff-5bd60e9e2857/v2.0/.well-known/openid-configuration
2025-07-01T18:59:12.538Z info: Outdated Config version: 1.2.1
Latest version: 1.2.8

  Check out the Config changelogs for the latest options and features added.

  https://... [truncated]

2025-07-01T18:59:12.778Z info: Configuring social logins...
2025-07-01T18:59:12.778Z info: Configuring OpenID Connect...
2025-07-01T18:59:12.930Z info: [indexSync] Messages are fully synced: 3407/3407
2025-07-01T18:59:12.935Z info: [indexSync] Conversations are fully synced: 468/468
2025-07-01T18:59:12.935Z debug: [indexSync] No sync was needed
2025-07-01T18:59:12.950Z info: OpenID Connect configured.
2025-07-01T18:59:12.954Z info: Server listening on all interfaces at port 3080. Use http://localhost:3080 to access it
2025-07-01T19:11:53.430Z info: Cleaning up FlowStateManager intervals...
2025-07-01T19:12:06.412Z info: [Optional] Redis not initialized.
2025-07-01T19:12:07.729Z info: [Optional] IoRedis not initialized for rate limiters.
2025-07-01T19:12:07.845Z info: Connected to MongoDB
2025-07-01T19:12:07.846Z info: [indexSync] Starting index synchronization check...

[samuelhalff]

@danny-avila I uploaded a screenshot, I don't see the same options as you do when clicking on the paperclip icon.
Thanks so much for your help, Librechat is amazing.

[danny-avila]

what is the value of your ENDPOINTS env. var?

Not seeing the options means the endpoints query is not returning any capabilities:

you should inspect the network tab for this route via chrome dev tools (or a similar browser inspect tool)

[samuelhalff]

My endpoints: ENDPOINTS=azureOpenAI,azureAssistants What am I missing ?

…

On Wed, 2 Jul 2025 at 16:49, Danny Avila ***@***.***> wrote: what is the value of your ENDPOINTS env. var? Not seeing the options means the endpoints query is not returning any capabilities: chrome_wh7H59moxW.png (view on web) <https://github.com/user-attachments/assets/e37de9e6-368e-445b-8115-b5574e541413> chrome_8eerSJxxYj.png (view on web) <https://github.com/user-attachments/assets/09e10c39-6869-4630-b959-c484429e198c> you should inspect the network tab for this route via chrome dev tools (or a similar browser inspect tool) — Reply to this email directly, view it on GitHub <#8172 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFBEXVUXY5FW76NGEFSH4T3GPWOTAVCNFSM6AAAAACAR6ZC52VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNRUGIYDQNA> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[samuelhalff]

Ok so I added "agents, assistants" to .env, and now the options appear.
I'm not sure why I need to enable agents or assistants as endpoints for OCR to be available (or in other words "Upload as text" to be available), but it works.

[danny-avila]

Thanks for getting back to me. Indeed that should be changed now that all the options are streamlined.

[samuelhalff]

Thanks. Now I’m struggling to get azure mistral ocr working. I followed the documentation but I get a 404 error, unclear how to fix the url here, all other azure endpoints and models work..

…

On Thu, 3 Jul 2025 at 17:46, Danny Avila ***@***.***> wrote: Thanks for getting back to me. Indeed that should be changed now that all the options are streamlined. — Reply to this email directly, view it on GitHub <#8172 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFBEXXHQUVCI45N3ZVU2YT3GVF4JAVCNFSM6AAAAACAR6ZC52VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNRVGQZDINY> . You are receiving this because you authored the thread.Message ID: ***@***.***>