.env

# ==========================================
# RAG API Environment Configuration
# ==========================================

# --- API Settings ---
PROJECT_NAME="RAG API Service"

# --- Qdrant (Vector Database) ---
QDRANT_URL=https://41524d5c-8b82-4106-84b9-db452ef40133.eu-central-1-0.aws.cloud.qdrant.io:6333
QDRANT_API_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhY2Nlc3MiOiJtIiwic3ViamVjdCI6ImFwaS1rZXk6NzY2MTRlMWUtNDJmMi00MDVkLTgxMWMtYjAyZDgwOGZjZDM0In0.QcECySpQnj1wzpif1k3K1G6Dz-PW9K5eNZ1ueNnn-IY
QDRANT_HOST=localhost
QDRANT_PORT=6333
QDRANT_COLLECTION=news_articles

# --- ClickHouse (Data Warehouse Analytics) ---
CLICKHOUSE_HOST=emrsjlb12r.eu-central-1.aws.clickhouse.cloud
CLICKHOUSE_PORT=8443
CLICKHOUSE_USER=default
CLICKHOUSE_PASSWORD=hOKAH9T9LoQ.m
CLICKHOUSE_SECURE=true

# --- PostgreSQL (Interactions & Accounts DB) ---
POSTGRES_USER=postgres
POSTGRES_PASSWORD=postgres
POSTGRES_SERVER=localhost
POSTGRES_PORT=5433
POSTGRES_DB=rag_interactions

# --- Models configuration ---
EMBEDDING_MODEL=BAAI/bge-m3
VECTOR_SIZE=1024
RERANKER_MODEL=BAAI/bge-reranker-v2-m3

# ==========================================
# LLM Provider — set LLM_PROVIDER to one of:
#   groq      → Free, 200+ tok/s, best for production (recommended)
#   gemini    → Free tier 15 RPM / 1M TPM, great quality
#   together  → Free $25 credit, Llama 3.3 70B
#   openai    → Paid, GPT-4o
#   ollama    → Local inference (no API key needed)
# ==========================================
LLM_PROVIDER=groq

# --- Groq (FREE) ---
# Get key: https://console.groq.com/keys
# Models: llama-3.3-70b-versatile | llama-3.1-8b-instant | mixtral-8x7b-32768 | gemma2-9b-it
GROQ_API_KEY=your-groq-api-key-here
GROQ_MODEL=llama-3.3-70b-versatile

# --- Google Gemini (FREE tier) ---
# Get key: https://aistudio.google.com/apikey
# Models: gemini-2.0-flash | gemini-1.5-flash | gemini-1.5-pro
GEMINI_API_KEY=AIzaSyB-LlAj_nhxRNpHzqBhxIMDc4R8eaDaYYI
GEMINI_MODEL=gemini-2.0-flash

# --- Together AI (FREE $25 credit) ---
# Get key: https://api.together.ai
# Models: meta-llama/Llama-3.3-70B-Instruct-Turbo | mistralai/Mixtral-8x7B-Instruct-v0.1
TOGETHER_API_KEY=key_CaW4uNxnNyzsFUcaYhB8y
TOGETHER_MODEL=meta-llama/Llama-3.3-70B-Instruct-Turbo

# --- OpenAI (Paid) ---
OPENAI_API_KEY=your-openai-api-key-here

# --- Ollama (Local) ---
# Run: ollama pull llama3.2
OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=llama3.2

# --- Redis Semantic Caching ---
REDIS_HOST=localhost
REDIS_PORT=6380
REDIS_DB=0
REDIS_PASSWORD=

# --- Security & Auth ---
SECRET_KEY=a_very_secret_key_change_me_in_production
ACCESS_TOKEN_EXPIRE_MINUTES=60

# --- Hybrid Search Settings ---
ENABLE_HYBRID_SEARCH=true
LIVE_SEARCH_TIMEOUT=2.0
LIVE_SEARCH_MAX_RESULTS=5
LIVE_SEARCH_WEIGHT=0.5
DB_SEARCH_WEIGHT=0.5

# --- Jina Reader Settings (Full Article Extraction) ---
# Extracts full article content from URLs (71x more content than snippets)
ENABLE_JINA_READER=true
JINA_READER_TIMEOUT=8.0
JINA_READER_MAX_CONCURRENT=5

# --- Kafka Settings (Top Stories — read-only consumer) ---
KAFKA_BOOTSTRAP_SERVERS=kafka-23e11337-weldamedhan2020-b406.i.aivencloud.com:20010
KAFKA_TOPIC_PROCESSED=news.processed
# SSL certs are read from /tmp/ — written at startup from env vars or cert files
# Set these to the content of your Aiven SSL certificates (newlines as \n)
# KAFKA_SSL_CA=<content of ca.pem>
# KAFKA_SSL_CERT=<content of service.cert>
# KAFKA_SSL_KEY=<content of service.key>

# Live Search Engine Configuration
LIVE_SEARCH_PRIMARY=searxng
LIVE_SEARCH_FALLBACK=duckduckgo

# SearXNG Settings (internal Docker network)
SEARXNG_ENABLED=true
SEARXNG_BASE_URL=http://searxng:8080
SEARXNG_TIMEOUT=5.0
SEARXNG_MAX_RESULTS=10