ErrorCode 500, cannot unmarshal array into Go struct field Message.messages.content of type string

[monsterlady]

LocalAI version:

quay.io/go-skynet/local-ai:v1.40.0-cublas-cuda12-ffmpeg

Environment, CPU architecture, OS, and Version:

Linux c970feda3bb9 5.15.133.1-microsoft-standard-WSL2 #1 SMP Thu Oct 5 21:02:42 UTC 2023 x86_64 GNU/Linux

Describe the bug

1. follow the doc to setup GPT vision
2. create yaml file

   backend: llama
   context_size: 4096
   f16: true
   threads: 1
   gpu_layers: 90
   mmap: true
   name: llava
   roles:
   user: "USER:"
   assistant: "ASSISTANT:"
   system: "SYSTEM:"
   parameters:
   model: ggml-model-q4_k.gguf
   temperature: 0.2
   top_k: 40
   top_p: 0.95
   template:
   chat: chat-simple
   mmproj: mmproj-model-f16.gguf

3. docker-compose up -d
4. send request by postman curl --location 'http://localhost:7080/v1/chat/completions' \ --header 'Content-Type: application/json' \ --data '{ "model": "llava", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What is in the image?" }, { "type": "image_url", "image_url": { "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } } ], "temperature": 0.9 } ] }'
5. get error { "error": { "code": 500, "message": "failed reading parameters from request:json: cannot unmarshal array into Go struct field Message.messages.content of type string", "type": "" } }

To Reproduce

above

Expected behavior

should have returned 200 with text

Logs

Additional context

[mudler]

llava is supported only on master and on 2.0. Closing the issue