Ireneusz Bachanowicz
2763b40b60
Some checks are pending
CI/CD Pipeline / test (push) Waiting to run
- Simplified the FastAPI application structure and improved error handling with middleware. - Introduced a retry decorator for asynchronous functions to enhance reliability. - Modularized the LLM initialization and prompt loading into separate functions for better maintainability. - Updated Pydantic models for Jira webhook payload and analysis flags to ensure proper validation and structure. - Implemented a structured logging configuration for better traceability and debugging. - Added comprehensive unit tests for prompt loading, response validation, and webhook handling. - Established a CI/CD pipeline with GitHub Actions for automated testing and coverage reporting. - Enhanced the prompt template for LLM analysis to include specific instructions for handling escalations.
31 lines
974 B
YAML
31 lines
974 B
YAML
# Default application configuration
|
|
llm:
|
|
# The mode to run the application in.
|
|
# Can be 'openai' or 'ollama'.
|
|
# This can be overridden by the LLM_MODE environment variable.
|
|
mode: ollama
|
|
|
|
# Settings for OpenAI-compatible APIs (like OpenRouter)
|
|
openai:
|
|
# It's HIGHLY recommended to set this via an environment variable
|
|
# instead of saving it in this file.
|
|
# Can be overridden by OPENAI_API_KEY
|
|
api_key: "sk-or-v1-..."
|
|
|
|
# Can be overridden by OPENAI_API_BASE_URL
|
|
api_base_url: "https://openrouter.ai/api/v1"
|
|
|
|
# Can be overridden by OPENAI_MODEL
|
|
model: "deepseek/deepseek-chat:free"
|
|
|
|
# Settings for Ollama
|
|
ollama:
|
|
# Can be overridden by OLLAMA_BASE_URL
|
|
base_url: "http://192.168.0.122:11434"
|
|
# base_url: "https://api-amer-sandbox-gbl-mdm-hub.pfizer.com/ollama"
|
|
|
|
# Can be overridden by OLLAMA_MODEL
|
|
model: "phi4-mini:latest"
|
|
# model: "qwen3:1.7b"
|
|
# model: "mollm:360m"
|
|
|