denissa4/agentbot repository overview

⁠API-server

Example local build cmd:

docker build -f Dockerfile -t nlsql-api-server .

Example local run cmd:

docker run --rm -p 8080:80 --env-file .env nlsql-api-server

Docker env params:

• DatabaseType (Options: 'mysql', 'mssql', 'snowflake', 'redshift', 'postgresql', 'bigquery')
• DataSource (For 'snowflake' analogue of the 'Account' db parameter)
• Warehouse (Used when DataSource='snowflake')
• DbSchema (Used when DataSource='snowflake')
• DbName
• DbUser
• DbPassword
• DbPort (Used when DataSource is 'mysql' or 'postgresql')
• ApiEndPoint
• ApiToken
• AppId
• AuthTenantID (Optional)
• AppPassword
• StaticEndPoint
• client_email (_Used when DataSource='bigquery'*)
• token_uri (_Used when DataSource='bigquery'*)
• private_key (_Used when DataSource='bigquery'*)
• project_id (_Used when DataSource='bigquery'*)
• FromYear (Starting year from which to measure trusted data)
• ToYear (The final year up to which trusted data is measured (inclusive))
• CorridorsMode (1 = standard mode (flat corridors over given time period, minimum 1 year of data); 2 = seasonal mode (monthly calculated corridors, minimum 2 years' of data))
• WindowSize (Size of the rolling window when using seasonal corridors mode (default = 5))
• BoundarySensitivity (Sensitivity for the lower and upper bounds for anomaly detection (mean +- BoundarySensitivity * standard deviation))
• EmailAddress (Email address for sending anomaly detection email)
• EmailPassword (Password for senders email (app password may need to be used for gmail and outlook accounts))
• RecipientEmail (Email addresses of recipients (seperated by comma (no space)))
• AzureAppName (Azure app name where interactive graph files are stored)
• OpenAiAPI (API key for OpenAI integration (informative emails))
• OpenAiBase (Base URL for OpenAI integration)
• OpenAiType (Type of OpenAI service, (e.g. azure))
• OpenAiVersion (Open AI version)
• OpenAiName (Name of OpenAI model to be used)
• SystemMessage (System Message for OpenAI for initial context and instructions given to OpenAI model)
• Frequency (Frequency (in days) for which the anomaly detection should take place)

API endpoint: /nlsql-analyzer

Method: POST

JSON: {"channel_id": str, "text": str}

⁠Nginx

location ~* \.(jpg|jpeg|gif|png|css|zip|tgz|gz|rar|bz2|doc|xls|exe|pdf|ppt|tar|mid|midi|wav|bmp|rtf|js|swf|docx|xlsx|svg|csv|html)$ to root /var/www/html

location /api/messages to proxy_pass http://localhost:8000

⁠Talk-to-Docs tests

Ensure the minimum requirements for tests are installed:

azure-ai-inference 
azure-identity 
azure-storage-blob 
faiss-cpu 
gpt4all
nomic 
odfpy 
openai 
openpyxl 
pypdf
PyPDF2
pytest-asyncio
python-docx

run cd api/talk_to_docs

run pytest -v

There should be 42 tests across 10 different functions.