Bug: ai container died

[yiruchen1993]

Steps to reproduce the behavior

1. click summarize thread for a post
2. See error: Sorry! An error occoured while accessing the LLM. See server logs for details. and the ai container died.

Expected behavior

"AI assistance" should respond me like the demo Vedio

Screenshots (optional)

I've followed the steps of Install local

1. I login to my local Mattermost with the given account (root)
2. post a message "test" at AI channel, then click summarize thread
3. I got the error "An error occoured while accessing the LLM. See server logs for details.", and the container of ai stopped (died)

4. here's the logs:

[127.0.0.1]:35824  200  -  GET      /readyz
3:10AM DBG Request received: {"model":"gpt4all-j","file":"","language":"","response_format":"","size":"","prompt":null,"instruction":"","input":null,"stop":null,"messages":[{"role":"system","content":"You are a helpful assistant.\n\nYou are an expert that summarizes threads.\nWhen the user gives you a thread, return a summary of the thread using less than 30 words.\nDo not refer to the thread, just give the summary."},{"role":"user","content":"The thread is given below:\n\n---- Thread Start ----\nroot: test\n\n\n---- Thread End ----"}],"stream":true,"echo":false,"top_p":1,"top_k":0,"temperature":1,"max_tokens":0,"n":0,"batch":0,"f16":false,"ignore_eos":false,"repeat_penalty":0,"n_keep":0,"mirostat_eta":0,"mirostat_tau":0,"mirostat":0,"frequency_penalty":0,"tfz":0,"seed":0,"mode":0,"step":0,"typical_p":0}
3:10AM DBG Parameter Config: &{OpenAIRequest:{Model:gpt4all-j File: Language: ResponseFormat: Size: Prompt:<nil> Instruction: Input:<nil> Stop:<nil> Messages:[] Stream:false Echo:false TopP:1 TopK:80 Temperature:1 Maxtokens:512 N:0 Batch:0 F16:false IgnoreEOS:false RepeatPenalty:0 Keep:0 MirostatETA:0 MirostatTAU:0 Mirostat:0 FrequencyPenalty:0 TFZ:0 Seed:0 Mode:0 Step:0 TypicalP:0} Name: StopWords:[] Cutstrings:[] TrimSpace:[] ContextSize:512 F16:false Threads:4 Debug:true Roles:map[] Embeddings:false Backend: TemplateConfig:{Completion: Chat: Edit:} MirostatETA:0 MirostatTAU:0 Mirostat:0 NGPULayers:0 MMap:false MMlock:false TensorSplit: MainGPU: ImageGenerationAssets: PromptCachePath: PromptCacheAll:false PromptCacheRO:false PromptStrings:[] InputStrings:[] InputToken:[]}
3:10AM DBG Stream request received
3:10AM 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:
You are a helpful assistant.

You are an expert that summarizes threads.
When the user gives you a thread, return a summary of the thread using less than 30 words.
Do not refer to the thread, just give the summary.
The thread is given below:

---- Thread Start ----
root: test


---- Thread End ----
### Response:
3:10AM DBG Loading model 'gpt4all-j' greedly
3:10AM DBG [llama] Attempting to load
3:10AM DBG Loading model llama from gpt4all-j
3:10AM DBG Loading model in memory from file: /models/gpt4all-j
[172.18.0.4]:58962  200  -  POST     /chat/completions
3:10AM DBG Sending chunk: {"object":"chat.completion.chunk","model":"gpt4all-j","choices":[{"delta":{"role":"assistant"}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

llama.cpp: loading model from /models/gpt4all-j
[127.0.0.1]:35968  200  -  GET      /readyz
/build/entrypoint.sh: line 11:     8 Killed                  ./local-ai "$@"

5. my plugin settings

        "Plugins": {
            "mattermost-ai": {
                "llmgenerator": "openaicompatible",
                "openaicompatiblemodel": "gpt4all-j",
                "openaicompatibleurl": "http://localai:8080"
            },
            "playbooks": {
                "BotUserID": "1sr9zhjjm7fq7fyrfxypy1ycoy"
            }
        },
        "PluginStates": {
            "com.mattermost.calls": {
                "Enable": true
            },
            "com.mattermost.nps": {
                "Enable": true
            },
            "mattermost-ai": {
                "Enable": true
            },
            "playbooks": {
                "Enable": true
            }
        }

Version and Platform

• Version: Mattermost Team Edition
  • Mattermost Version: 8.1.0
  • Database Schema Version: 109
  • Database: postgres
• quay.io/go-skynet/local-ai: v0.19.0
• Browser and OS: Chrome on Mac, 116.0.5845.140