BUG with chatbot-ui: model does not exist

[chenbt-hz]

llama: model does not exist gpt: model does not exist gpt2: model does not exist stableLM: model does not exist

The UI interface cannot be used, and the page cannot select a local model. I am using 'ggml gpt4all j' locally

I think it is due to the following configuration not being added in the image. https://github.com/mckaywrigley/chatbot-ui/blob/main/types/openai.ts

Here： export const fallbackModelID = OpenAIModelID.GPT_3_5;

[chenbt-hz]

Maybe it's another problem

This is the file I referenced and build in MacOS: https://github.com/go-skynet/LocalAI/tree/master/examples/chatbot-ui

[ksingh7]

@chenbt-hz can you share your chatbot-ui docker file ? or how your UI is interacting with APIs ? would like to review that

[chenbt-hz]

After I pulled the latest version and modified the configuration as follows, the error prompt on the web no longer appears, but new errors still appear。

examples/chatbot-ui/docker-compose.yaml: `version: '3.6'

services: api: image: quay.io/go-skynet/local-ai:latest build: context: ../../ dockerfile: Dockerfile.dev ports: - 8080:8080 environment: - DEBUG=true - MODELS_PATH=/models volumes: - ./models:/models:cached command: ["/usr/bin/local-ai" ]

chatgpt: image: ghcr.io/mckaywrigley/chatbot-ui:main ports: - 3000:3000 environment: - 'OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXXXXXX' - 'OPENAI_API_HOST=http://:8080'`

examples/chatbot-ui/models/gpt-3.5-turbo.yaml: `name: gpt-3.5-turbo parameters: model: ggml-gpt4all-j top_k: 80 temperature: 0.2 top_p: 0.7 context_size: 1024 threads: 4 backend: gptj stopwords:

• "HUMAN:"
• "GPT:"
• "### Response:" roles: user: "HUMAN:" system: "GPT:" template: completion: completion chat: ggml-gpt4all-j`

[chenbt-hz]

I tried to start the model in Docker, but got the problem that computation crashing when asked. Eventually, I used a local build and successfully started the service `./local-ai --models-path ./models/ --debug Starting LocalAI using 4 threads, with models path: ./models/

┌───────────────────────────────────────────────────┐ │ Fiber v2.44.0 │ │ http://127.0.0.1:8080 │ │ (bound on host 0.0.0.0 and port 8080) │ │ │ │ Handlers ............ 12 Processes ........... 1 │ │ Prefork ....... Disabled PID ............. 72719 │ └───────────────────────────────────────────────────┘

11:35AM DBG Request received: {"model":"","prompt":null,"instruction":"","input":"","stop":null,"messages":null,"stream":false,"echo":false,"top_p":0,"top_k":0,"temperature":0,"max_tokens":0,"n":0,"batch":0,"f16":false,"ignore_eos":false,"repeat_penalty":0,"n_keep":0,"seed":0} 11:35AM DBG No model specified, using: ggml-gpt4all-j 11:35AM DBG Parameter Config: &{OpenAIRequest:{Model:ggml-gpt4all-j Prompt: Instruction: Input: Stop: Messages:[] Stream:false Echo:false TopP:0.7 TopK:80 Temperature:0.9 Maxtokens:512 N:0 Batch:0 F16:false IgnoreEOS:false RepeatPenalty:0 Keep:0 Seed:0} Name: StopWords:[] Cutstrings:[] TrimSpace:[] ContextSize:512 F16:false Threads:4 Debug:true Roles:map[] Backend: TemplateConfig:{Completion: Chat: Edit:}} 11:35AM DBG Template found, input modified to: The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.

Prompt:

Response:

`