RAG-ChatBot/.env.example at main · IRONalways17/RAG-ChatBot · 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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
# RAG Q&A Chatbot Environment Configuration

# ==============================================
# LLM API KEYS (Choose your preferred provider)
# ==============================================

# OpenAI (GPT models) - Get free credits at platform.openai.com
OPENAI_API_KEY=your_openai_api_key_here

# Anthropic Claude - Get free credits at console.anthropic.com
ANTHROPIC_API_KEY=your_anthropic_api_key_here

# Google Gemini - Free tier available at makersuite.google.com
GOOGLE_API_KEY=your_google_api_key_here

# Cohere - Free tier available at cohere.ai
COHERE_API_KEY=your_cohere_api_key_here

# Hugging Face (for free models) - Sign up at huggingface.co
HUGGINGFACE_API_KEY=your_huggingface_api_key_here

# ==============================================
# DEFAULT LLM CONFIGURATION
# ==============================================

# Available options: openai, anthropic, google, cohere, huggingface
DEFAULT_LLM_PROVIDER=huggingface

# Model configurations for each provider
OPENAI_MODEL=gpt-3.5-turbo
ANTHROPIC_MODEL=claude-3-haiku-20240307
GOOGLE_MODEL=gemini-pro
COHERE_MODEL=command-light
HUGGINGFACE_MODEL=microsoft/DialoGPT-medium

# ==============================================
# SERVER CONFIGURATION
# ==============================================

PORT=3000
NODE_ENV=development

# ==============================================
# EMBEDDING CONFIGURATION
# ==============================================

# For document embeddings (free options available)
EMBEDDING_PROVIDER=huggingface
EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

# ==============================================
# VECTOR DATABASE CONFIGURATION
# ==============================================

# Simple in-memory storage (no external DB needed)
VECTOR_DB_TYPE=memory
MAX_DOCUMENTS=1000
CHUNK_SIZE=500
CHUNK_OVERLAP=50

# ==============================================
# RETRIEVAL CONFIGURATION
# ==============================================

TOP_K_RESULTS=5
SIMILARITY_THRESHOLD=0.7
MAX_CONTEXT_LENGTH=4000

# ==============================================
# RATE LIMITING
# ==============================================

RATE_LIMIT_REQUESTS=100
RATE_LIMIT_WINDOW=900000

# ==============================================
# SECURITY
# ==============================================

SESSION_SECRET=your_random_session_secret_here
CORS_ORIGIN=http://localhost:3000