rag-fundamentals-workshop/env.example at main · learnwithparam/rag-fundamentals-workshop · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
# RAG Fundamentals Workshop - Environment Variables
# Copy this file to .env and fill in your API keys

# ============================================================================
# REQUIRED: At least ONE of these LLM API keys is required
# ============================================================================

# Google AI (Gemini) - Get free key at: https://aistudio.google.com/apikey
# Recommended for this workshop (Free tier available)
GOOGLE_API_KEY=your-google-api-key-here

# OpenAI - Get key at: https://platform.openai.com/api-keys
# Optional: Use if you want to test with GPT-4o, GPT-4o-mini, etc.
OPENAI_API_KEY=your-openai-api-key-here

# Anthropic (Claude) - Get key at: https://console.anthropic.com/
# Optional: Use if you want to test with Claude 3.5 Sonnet, etc.
ANTHROPIC_API_KEY=your-anthropic-api-key-here

# ============================================================================
# MODEL CONFIGURATION (via LiteLLM)
# ============================================================================

# Default model to use for text generation across all notebooks.
# LiteLLM allows you to use shorthand names for different providers.
#
# How to use with LiteLLM:
# - Gemini:  gemini/gemini-2.0-flash-exp (Requires GOOGLE_API_KEY)
# - OpenAI:  gpt-4o-mini (Requires OPENAI_API_KEY)
# - Anthropic: claude-3-5-sonnet-20241022 (Requires ANTHROPIC_API_KEY)
# - OpenRouter: openrouter/google/gemini-2.0-flash-exp:free (Requires OPENROUTER_API_KEY)
DEFAULT_MODEL=gemini/gemini-2.0-flash-exp

# Model to use for generating vector embeddings.
# Note: Different models produce different vector sizes (dimensions).
# Example: text-embedding-004 (Google) or text-embedding-3-small (OpenAI)
EMBEDDING_MODEL=google/text-embedding-004

# ============================================================================
# VECTOR STORE: QDRANT
# ============================================================================

# Qdrant is running via Docker Compose by default.
# Port 6333 is the REST API port used by the qdrant-client.
QDRANT_URL=http://localhost:6333
QDRANT_API_KEY=

# ============================================================================
# OPTIONAL: OpenRouter (Alternative to direct API keys)
# ============================================================================

# OpenRouter - Get key at: https://openrouter.ai/
# Provides access to multiple models through one unified API.
# OPENROUTER_API_KEY=your-openrouter-api-key-here

# ============================================================================
# NOTES & BEST PRACTICES
# ============================================================================

# 1. SECURITY: Never commit your .env file to version control (Git).
# 2. PRIORITY: If multiple keys are set, LiteLLM handles routing automatically based on the DEFAULT_MODEL prefix.
# 3. COST: Be mindful of token usage when using paid tiers (OpenAI/Anthropic).
# 4. SETUP: Run 'cp env.example .env' and then fill in your keys.