# Aktiveeri venv source ~/venvs/pdf-env/bin/activate cd ~/rag-demo/pdf-pipeline export $(grep -v '^#' .env | xargs -d '\n') python -m src.db_schema # uuesti skeemiga # Vektor välja muudatus ./scripts/db_vector_välja_muutmine.sh python -m src.extract_pdf # parandatud ekstraheerimisega python -m src.check_status # parema ülevaatega python -m src.find_duplicates # duplikaatide kontroll # dokumentide protsessimine python -m src.clean_and_normalize python -m src.create_chunks # Järgmises koodis on parameeter BATCH_LIMIT # Nii kaua tuleb käivitada koodi kuni kõik embeddingud on lisatud python -m src.embed_chunks # Weaviate baasiga sünkroniseerimine python -m src.sync_weaviate # Testimine docker exec -it postgres_postgis psql -U osm -d pdf_research -h localhost -c "SELECT COUNT(*) FROM processed_documents;" docker exec -it postgres_postgis psql -U osm -d pdf_research -h localhost -c " SELECT id, raw_doc_id, page, LENGTH(content_text) AS len, has_table FROM processed_documents ORDER BY id LIMIT 20; " python -m src.query_hybrid python -m src.generate_answer # API käivitamine python -m src.rag_api ## ============================================================== ## API päringute näidised ### 1. **Interactive Docs** (Swagger UI) Ava brauseris: ``` http://localhost:8071/docs ``` ### 2. **cURL käsuga** ```bash # Lihtsustatud otsing curl "http://localhost:8000/search-simple?q=young%20driver%20risk" # POST requestiga (täielik kontroll) curl -X POST "http://localhost:8071/search" \ -H "Content-Type: application/json" \ -d '{ "query": "young driver accident risk", "top_articles": 10, "top_chunks": 20, "temperature": 0.6, "max_tokens": 1500 }' | jq '.' ``` ### 3. **Python requestiga** ```python import requests import json # POST päring response = requests.post( "http://localhost:8071/search", json={ "query": "traffic flow prediction", "top_articles": 10, "top_chunks": 20, "temperature": 0.6, "max_tokens": 1500 } ) result = response.json() print("Küsimus:", result["query"]) print("Vastus:", result["answer"]) print("Allikad:", result["articles"]) ```