search

stitionai / devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.
MIT License
17.8k stars 2.32k forks source link

Devika AI is not responding when any text is searched #473

Open neerajkm22 opened 2 months ago

neerajkm22 commented 2 months ago

Devika AI is not responding when any text is searched. I tried with multiple combinations of model and search engine. Still no luck, it seems there is an issue with api response.

theguy000 commented 2 months ago

post logs

neerajkm22 commented 2 months ago

Here is the log

PS D:\devikaAi> cd .\devika\ PS D:\devikaAi\devika> python .\devika.py 24.04.23 15:21:09: root: INFO : Initializing Devika... 24.04.23 15:21:09: root: INFO : Initializing Prerequisites Jobs...
24.04.23 15:21:14: root: INFO : Loading sentence-transformer BERT models... 24.04.23 15:21:18: root: INFO : BERT model loaded successfully.
24.04.23 15:21:19: root: INFO : Ollama available 24.04.23 15:21:21: root: INFO : Devika is up and running! Socket connected :: {'data': 'frontend connected!'} 24.04.23 15:28:18: root: INFO : SOCKET socket_response MESSAGE: {'data': 'Server Connected'} 24.04.23 15:28:18: root: INFO : /api/data GET 24.04.23 15:28:18: root: DEBUG : /api/data GET - Response: {"models":{"CLAUDE":[["Claude 3 Opus","claude-3-opus-20240229"],["Claude 3 Sonnet","claude-3-sonnet-20240229"],["Claude 3 Haiku","claude-3-haiku-20240307"]],"GOOGLE":[["Gemini 1.0 Pro","gemini-pro"]],"GROQ":[["LLAMA3 8B","llama3-8b-8192"],["LLAMA3 70B","llama3-70b-8192"],["LLAMA2 70B","llama2-70b-4096"],["Mixtral","mixtral-8x7b-32768"],["GEMMA 7B","gemma-7b-it"]],"MISTRAL":[["Mistral 7b","open-mistral-7b"],["Mistral 8x7b","open-mixtral-8x7b"],["Mistral Medium","mistral-medium-latest"],["Mistral Small","mistral-small-latest"],["Mistral Large","mistral-large-latest"]],"OLLAMA":[],"OPENAI":[["GPT-4 Turbo","gpt-4-turbo"],["GPT-3.5 Turbo","gpt-3.5-turbo-0125"]]},"projects":["rama"],"search_engines":["Bing","Google","DuckDuckGo"]}

24.04.23 15:28:18: root: INFO : /api/get-agent-state POST 24.04.23 15:28:18: root: DEBUG : /api/get-agent-state POST - Response: {"state":null}

24.04.23 15:28:21: root: INFO : /api/get-agent-state POST 24.04.23 15:28:21: root: DEBUG : /api/get-agent-state POST - Response: {"state":{"agent_is_active":true,"browser_session":{"screenshot":null,"url":null},"completed":false,"internal_monologue":null,"message":null,"step":null,"terminal_session":{"command":null,"output":null,"title":null},"timestamp":"2024-04-22 12:35:09","token_usage":370}}

24.04.23 15:28:33: root: INFO : SOCKET server-message MESSAGE: {'messages': {'from_devika': False, 'message': 'Write code in java script to multiply two numbers', 'timestamp': '2024-04-23 15:28:33'}}

neerajkm22 commented 2 months ago

Request logs 24.04.23 15:28:21: root: DEBUG : /api/get-agent-state POST - Response: {"state":{"agent_is_active":true,"browser_session":{"screenshot":null,"url":null},"completed":false,"internal_monologue":null,"message":null,"step":null,"terminal_session":{"command":null,"output":null,"title":null},"timestamp":"2024-04-22 12:35:09","token_usage":370}}

24.04.23 15:28:21: root: INFO : /api/get-agent-state POST

24.04.23 15:28:18: root: DEBUG : /api/get-agent-state POST - Response: {"state":null}

24.04.23 15:28:18: root: INFO : /api/get-agent-state POST

24.04.23 15:28:18: root: DEBUG : /api/data GET - Response: {"models":{"CLAUDE":[["Claude 3 Opus","claude-3-opus-20240229"],["Claude 3 Sonnet","claude-3-sonnet-20240229"],["Claude 3 Haiku","claude-3-haiku-20240307"]],"GOOGLE":[["Gemini 1.0 Pro","gemini-pro"]],"GROQ":[["LLAMA3 8B","llama3-8b-8192"],["LLAMA3 70B","llama3-70b-8192"],["LLAMA2 70B","llama2-70b-4096"],["Mixtral","mixtral-8x7b-32768"],["GEMMA 7B","gemma-7b-it"]],"MISTRAL":[["Mistral 7b","open-mistral-7b"],["Mistral 8x7b","open-mixtral-8x7b"],["Mistral Medium","mistral-medium-latest"],["Mistral Small","mistral-small-latest"],["Mistral Large","mistral-large-latest"]],"OLLAMA":[],"OPENAI":[["GPT-4 Turbo","gpt-4-turbo"],["GPT-3.5 Turbo","gpt-3.5-turbo-0125"]]},"projects":["rama"],"search_engines":["Bing","Google","DuckDuckGo"]}

24.04.23 15:28:18: root: INFO : /api/data GET

24.04.23 15:21:21: root: INFO : Devika is up and running!

24.04.23 15:21:19: root: INFO : Ollama available

24.04.23 15:21:18: root: INFO : BERT model loaded successfully.

24.04.23 15:21:14: root: INFO : Loading sentence-transformer BERT models...

24.04.23 15:21:09: root: INFO : Initializing Prerequisites Jobs...

24.04.23 15:21:09: root: INFO : Initializing Devika...

BartNetJS commented 2 months ago

I had the same issue. I saw this in my logs:

openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

and after correcting it, also this:

openai.PermissionDeniedError: Error code: 403 - {'error': {'message': 'Projectproj_xZIG3B04CTPZw2VmeQyVuaS4does not have access to modelgpt-3.5-turbo-0125', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}}

etc

and when one error occurs it all stops working. You have to create a new project to get it working again