Claude/docker deployment guide 015g1cum b lu mc ytpeq9cdeo8

.env.example

@@ -0,0 +1,59 @@
+# LLM Integration Configuration
+# Copy this file to .env and fill in your API keys
+
+# ============================================================================
+# LLM Provider Selection
+# ============================================================================
+# Choose: 'openai' or 'claude'
+LLM_PROVIDER=openai
+
+# ============================================================================
+# OpenAI Configuration
+# ============================================================================
+# Get your API key from: https://platform.openai.com/api-keys
+OPENAI_API_KEY=your-openai-api-key-here
+
+# Model options:
+# - gpt-4 (most capable, expensive)
+# - gpt-3.5-turbo (fast, cheap)
+OPENAI_MODEL=gpt-4
+
+# ============================================================================
+# Anthropic Claude Configuration
+# ============================================================================
+# Get your API key from: https://console.anthropic.com/
+ANTHROPIC_API_KEY=your-anthropic-api-key-here
+
+# Model options:
+# - claude-3-5-sonnet-20241022 (best performance)
+# - claude-3-haiku-20240307 (fast, cheap)
+CLAUDE_MODEL=claude-3-5-sonnet-20241022
+
+# ============================================================================
+# Hybrid Configuration
+# ============================================================================
+# Confidence threshold for LLM fallback (0.0 - 1.0)
+# If Rasa confidence < this value, use LLM
+CONFIDENCE_THRESHOLD=0.7
+
+# Ambiguity threshold for intent clarification
+# If top 2 intents differ by less than this, clarify with LLM
+AMBIGUITY_THRESHOLD=0.2
+
+# Number of previous messages to include as context
+CONTEXT_LENGTH=5
+
+# ============================================================================
+# Advanced Settings
+# ============================================================================
+# LLM temperature (0.0 = deterministic, 1.0 = creative)
+LLM_TEMPERATURE=0.7
+
+# Max tokens for LLM response
+LLM_MAX_TOKENS=500
+
+# Enable response caching (reduce API costs)
+ENABLE_LLM_CACHE=true
+
+# Log LLM requests for debugging
+LOG_LLM_REQUESTS=true