[GH-ISSUE #3237] [FEAT]: DeepSeek deployed on Azure AI Foundry #2084

Open
opened 2026-02-22 18:28:05 -05:00 by yindo · 2 comments
Owner

Originally created by @Chunlong101 on GitHub (Feb 16, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3237

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

DeepSeek deployed on Azure AI Foundry doesn't work in AnythingLLM v1.7.3-r2

Are there known steps to reproduce?

  1. Deploy the DeepSeek model on azure ai foundry
  2. In AnythingLLM v1.7.3-r2, create a new workspace, in the LLM providers, either select "Azure OpenAI" or "Generic OpenAI", no one is working for Azure AI Foundry:
    Image
    Image
  3. That’s because the api for DeepSeek deployed on Azure AI Foundry follows below format, it’s similar with Azure OpenAI but differs slightly:
curl -X POST "https://xxx.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview" \
  -H "Content-Type: application/json" \
  -H "api-key: YOUR_API_KEY" \
  -d '{
    "messages": [{"role": "system", "content": "You are an helpful assistant."}, {"role": "user", "content": "What are 3 things to visit in Seattle?"}],
    "max_tokens": 1000,
    "model": "DeepSeek-R1"
  }'
Originally created by @Chunlong101 on GitHub (Feb 16, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3237 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? DeepSeek deployed on Azure AI Foundry doesn't work in AnythingLLM v1.7.3-r2 ### Are there known steps to reproduce? 1. Deploy the DeepSeek model on azure ai foundry 2. In AnythingLLM v1.7.3-r2, create a new workspace, in the LLM providers, either select "Azure OpenAI" or "Generic OpenAI", no one is working for Azure AI Foundry: ![Image](https://github.com/user-attachments/assets/d6ae42b9-f206-4984-acea-a196c6273a16) ![Image](https://github.com/user-attachments/assets/9e76f569-4b20-4eb9-b780-07567fbd198d) 3. That’s because the api for DeepSeek deployed on Azure AI Foundry follows below format, it’s similar with Azure OpenAI but differs slightly: ``` curl -X POST "https://xxx.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview" \ -H "Content-Type: application/json" \ -H "api-key: YOUR_API_KEY" \ -d '{ "messages": [{"role": "system", "content": "You are an helpful assistant."}, {"role": "user", "content": "What are 3 things to visit in Seattle?"}], "max_tokens": 1000, "model": "DeepSeek-R1" }' ```
yindo added the Integration Request label 2026-02-22 18:28:05 -05:00
Author
Owner

@ZJianjin commented on GitHub (Feb 22, 2025):

Meet same problems here. Do we have any adhoc solutions to support it?

@ZJianjin commented on GitHub (Feb 22, 2025): Meet same problems here. Do we have any adhoc solutions to support it?
Author
Owner

@YaleGuo commented on GitHub (Feb 27, 2025):

Meet the same issue. I managed to access DeepSeek-R1 on Azure AI Foundry via Postman, but failed with AnythingLLM.

@YaleGuo commented on GitHub (Feb 27, 2025): Meet the same issue. I managed to access DeepSeek-R1 on Azure AI Foundry via Postman, but failed with AnythingLLM.
yindo changed title from [FEAT]: DeepSeek deployed on Azure AI Foundry to [GH-ISSUE #3237] [FEAT]: DeepSeek deployed on Azure AI Foundry 2026-06-05 14:44:26 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2084