use preciz SDK from pip package instead of local path

fix XML tool call parser for malformed key-value pairs

handle XML-style tool calls for models without native function calling

switch to openrouter/owl-alpha model, move model name to env var

fix: use onnxruntime directly without torch dependency

feat: switch to ONNX runtime for embeddings

refactor: remove Google AI, switch to OpenRouter, improve service runner

add promtps to docker path

add fallback

seperate prompts

remove logs

improved tool calling , prompt enhance

add tests

Integrate OpenRouter GLM model with RAG tool calling

Add /questions endpoint

Remove bolding from prompt examples

Add few-shot examples to prompt

Enhance prompt for better readability

Refine prompt for developer portfolio

Deploy RAG Pipeline with FastAPI and ML capabilities