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
17.96k stars 3k forks source link

[Bug]: Azureopen ai 404 model not found #3254

Closed Riser01 closed 3 months ago

Riser01 commented 3 months ago

What happened?

I am newly setting up the chat ui in local docker ,

i have tested the azureopen ai keys and model deployment with normal python code it works .

but it fails when i add it to the YAML config , its not clear what the error actually is

LibreChat | 2024-07-03 13:39:26 warn: [OpenAIClient.chatCompletion][stream] API error LibreChat | 2024-07-03 13:39:26 error: [handleAbortError] AI response error; aborting request: 404 Resource not found
chat-meilisearch | 2024-07-03T13:39:26.526786Z INFO HTTP request{method=POST host="meilisearch:7700" route=/indexes/messages/documents query_parameters= user_agent=node status_code=202}: meilisearch: close time.busy=2.84ms time.idle=7.95ms

Steps to Reproduce

below is the current config librechat.YAML

  azureOpenAI:
    titleModel: "gpt-4o"
    titleConvo: true
    plugins: false
    summarize: true
    groups:
      - group: "eastus" # arbitrary name
        apiKey: "xx"
        instanceName: "xx" # name of the resource group or instance
        version: "2024-02-01"
        # baseURL: "https://${INSTANCE_NAME}.openai.azure.com/openai/deployments/${DEPLOYMENT_NAME}"
        models:
          gpt-4o:
            deploymentName: "gpt-4o"
            version: "2024-05-13"
          dall-e-3:
            deploymentName: "dall-e-3"
            version: "3.0"
          gpt-35-turbo:
            deploymentName: "gpt-35-turbo"
            version: "0301"
          gpt-35-turbo-16k:
            deploymentName: "gpt-35-turbo-16k"
            version: "0613"
          text-embedding-3-large:
            deploymentName: "text-embedding-3-large"
            version: "1"
          text-embedding-3-small:
            deploymentName: "text-embedding-3-small"
            version: "1"
          text-embedding-ada-002:
            deploymentName: "text-embedding-ada-002"
            version: "2"
      - group: "francecentral" # arbitrary name
        apiKey: "xx"
        instanceName: "xx" # name of the resource group or instance
        version: "2024-02-15-preview"
        # baseURL: "https://${INSTANCE_NAME}.openai.azure.com/openai/deployments/${DEPLOYMENT_NAME}"
        models:
          gpt-4:
            deploymentName: "gpt-4"
            version: "0613"
          gpt-4-32k:
            deploymentName: "gpt-4-32k"
            version: "0613"

docker override config :

services:
  api:
    volumes:
    - type: bind
      source: ./librechat.yaml
      target: /app/librechat.yaml
    image: ghcr.io/danny-avila/librechat:latest

What browsers are you seeing the problem on?

No response

Relevant log output

LibreChat         | 2024-07-03 13:39:26 warn: [OpenAIClient.chatCompletion][stream] API error
LibreChat         | 2024-07-03 13:39:26 error: [handleAbortError] AI response error; aborting request: 404 Resource not found                                                                                                               
chat-meilisearch  | 2024-07-03T13:39:26.526786Z  INFO HTTP request{method=POST host="meilisearch:7700" route=/indexes/messages/documents query_parameters= user_agent=node status_code=202}: meilisearch: close time.busy=2.84ms time.idle=7.95ms

Screenshots

No response

Code of Conduct

Riser01 commented 3 months ago

the version was saposed to be api version not model version