Ollama local Embedding: miti99/gte-qwen2 + LLM: llama3.1:8b

.env

# Ollama local embedding、 llm 代替 openai 云端模型
# Ollama local Embedding: miti99/gte-qwen2 + LLM: llama3.1:8b
# 模板地址：https://github.com/plastic-labs/honcho/blob/main/.env.template
# Honcho Environment Variables Template
# Copy this file to .env and fill in the appropriate values
#
# Required variables are marked with (REQUIRED)
# Optional variables have default values and can be left commented out

# =============================================================================
# Application Settings
# =============================================================================
LOG_LEVEL=INFO
# SESSION_OBSERVERS_LIMIT=10
# GET_CONTEXT_MAX_TOKENS=100000
# MAX_FILE_SIZE=5242880 # Bytes
# MAX_MESSAGE_SIZE=25000 # Characters

# Embedding settings
# ✅ 明确启用embedding及维度
EMBED_MESSAGES=true
EMBEDDING_VECTOR_DIMENSIONS=1536
# EMBEDDING_MAX_INPUT_TOKENS=8192
# EMBEDDING_MAX_TOKENS_PER_REQUEST=300000

# ✅ Ollama Embedding（覆盖默认 OpenAI）
EMBEDDING_MODEL_CONFIG__TRANSPORT=openai
EMBEDDING_MODEL_CONFIG__MODEL=miti99/gte-qwen2
EMBEDDING_MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

# LANGFUSE_HOST=
# LANGFUSE_PUBLIC_KEY=

# COLLECT_METRICS_LOCAL=false
# LOCAL_METRICS_FILE=metrics.jsonl
# REASONING_TRACES_FILE=traces.jsonl  # Path to JSONL file for reasoning traces

# NAMESPACE="honcho"

# =============================================================================
# Database Settings (REQUIRED)
# =============================================================================
# Connection URI for PostgreSQL database with pgvector support
# Must use postgresql+psycopg prefix for SQLAlchemy compatibility
# # ✅ 修改为个人postgresql配置信息
DB_CONNECTION_URI=postgresql+psycopg://<username>:<passwor>@localhost:5432/honcho_db

# Optional database settings
# DB_SCHEMA=public
# DB_POOL_CLASS=default
# DB_POOL_SIZE=10
# DB_MAX_OVERFLOW=20
# DB_POOL_TIMEOUT=30
# DB_POOL_RECYCLE=300
# DB_POOL_PRE_PING=true
# DB_POOL_USE_LIFO=true
# DB_SQL_DEBUG=false
# DB_TRACING=false

# =============================================================================
# Authentication Settings
# =============================================================================
# Whether to enable authentication (set to true for production)
AUTH_USE_AUTH=false

# JWT secret key (REQUIRED if AUTH_USE_AUTH=true)
# Generate with: python scripts/generate_jwt_secret.py
# AUTH_JWT_SECRET=your-secret-key-here

# =============================================================================
# LLM Provider (REQUIRED) 
# =============================================================================
# ✅ Ollama 不需要真实 key，填任意字符串占位即可骗过校验
LLM_OPENAI_API_KEY=ollamalocal
# LLM_ANTHROPIC_API_KEY=
# LLM_GEMINI_API_KEY=

# =============================================================================
# LLM Configuration
# =============================================================================
# Global LLM settings
# LLM_DEFAULT_MAX_TOKENS=2500
# LLM_MAX_TOOL_OUTPUT_CHARS=10000  # Max chars for tool output (~2500 tokens)
# LLM_MAX_MESSAGE_CONTENT_CHARS=2000  # Max chars per message in tool results

# =============================================================================
# Deriver (Background Worker)
# =============================================================================
# DERIVER_ENABLED=true
# ✅ 切到 Ollama
DERIVER_MODEL_CONFIG__TRANSPORT=openai
DERIVER_MODEL_CONFIG__MODEL=llama3.1:8b
DERIVER_MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1
#DERIVER_MODEL_CONFIG__OVERRIDES__API_KEY_ENV=LLM_OPENAI_API_KEY

# =============================================================================
# Dialectic (Chat) 
# =============================================================================
# ✅ 全部切到 Ollama
DIALECTIC_LEVELS__minimal__MODEL_CONFIG__TRANSPORT=openai
DIALECTIC_LEVELS__minimal__MODEL_CONFIG__MODEL=llama3.1:8b
DIALECTIC_LEVELS__minimal__MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

DIALECTIC_LEVELS__low__MODEL_CONFIG__TRANSPORT=openai
DIALECTIC_LEVELS__low__MODEL_CONFIG__MODEL=llama3.1:8b
DIALECTIC_LEVELS__low__MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

DIALECTIC_LEVELS__medium__MODEL_CONFIG__TRANSPORT=openai
DIALECTIC_LEVELS__medium__MODEL_CONFIG__MODEL=llama3.1:8b
DIALECTIC_LEVELS__medium__MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

DIALECTIC_LEVELS__high__MODEL_CONFIG__TRANSPORT=openai
DIALECTIC_LEVELS__high__MODEL_CONFIG__MODEL=llama3.1:8b
DIALECTIC_LEVELS__high__MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

DIALECTIC_LEVELS__max__MODEL_CONFIG__TRANSPORT=openai
DIALECTIC_LEVELS__max__MODEL_CONFIG__MODEL=llama3.1:8b
DIALECTIC_LEVELS__max__MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1

# =============================================================================
# Summary 
# =============================================================================
# ✅ 切到 Ollama
SUMMARY_MODEL_CONFIG__TRANSPORT=openai
SUMMARY_MODEL_CONFIG__MODEL=llama3.1:8b
SUMMARY_MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1
#SUMMARY_MODEL_CONFIG__OVERRIDES__API_KEY_ENV=LLM_OPENAI_API_KEY

# =============================================================================
# Dream 
# =============================================================================
# ✅ 切到 Ollama
DREAM_MODEL_CONFIG__TRANSPORT=openai
DREAM_MODEL_CONFIG__MODEL=llama3.1:8b
DREAM_MODEL_CONFIG__OVERRIDES__BASE_URL=http://localhost:11434/v1
#DREAM_MODEL_CONFIG__OVERRIDES__API_KEY_ENV=LLM_OPENAI_API_KEY

# DREAM_MIN_HOURS_BETWEEN_DREAMS=8
# DREAM_ENABLED_TYPES=["omni"]
# DREAM_MAX_TOOL_ITERATIONS=20
# DREAM_HISTORY_TOKEN_LIMIT=16384

# Surprisal sampling (advanced):
# DREAM_SURPRISAL__ENABLED=false
# DREAM_SURPRISAL__TREE_TYPE=kdtree
# DREAM_SURPRISAL__TREE_K=5
# DREAM_SURPRISAL__SAMPLING_STRATEGY=recent
# DREAM_SURPRISAL__SAMPLE_SIZE=200
# DREAM_SURPRISAL__TOP_PERCENT_SURPRISAL=0.10
# DREAM_SURPRISAL__MIN_HIGH_SURPRISAL_FOR_REPLACE=10
# DREAM_SURPRISAL__INCLUDE_LEVELS=["explicit","deductive"]

# =============================================================================
# Webhook Settings
# =============================================================================
# WEBHOOK_SECRET=
# WEBHOOK_MAX_WORKSPACE_LIMIT=10

# =============================================================================
# Monitoring and Observability (Optional)
# =============================================================================
# Sentry error tracking
# SENTRY_ENABLED=false
# SENTRY_DSN=your-sentry-dsn-here
# SENTRY_RELEASE=your-release-semver
# SENTRY_ENVIRONMENT=development
# SENTRY_TRACES_SAMPLE_RATE=0.1
# SENTRY_PROFILES_SAMPLE_RATE=0.1

# =============================================================================
# Prometheus Metrics Settings (Pull-based metrics)
# =============================================================================
# METRICS_ENABLED=false
# METRICS_NAMESPACE=honcho  # Inherits from NAMESPACE if not set

# =============================================================================
# CloudEvents Telemetry Settings (Analytics events)
# =============================================================================
# TELEMETRY_ENABLED=false
# TELEMETRY_ENDPOINT=https://telemetry.honcho.dev/v1/events
# TELEMETRY_HEADERS={"Authorization": "Bearer your-token"}  # JSON string for auth headers
# TELEMETRY_BATCH_SIZE=100
# TELEMETRY_FLUSH_INTERVAL_SECONDS=1.0
# TELEMETRY_FLUSH_THRESHOLD=50
# TELEMETRY_MAX_RETRIES=3
# TELEMETRY_MAX_BUFFER_SIZE=10000
# TELEMETRY_NAMESPACE=honcho  # Inherits from NAMESPACE if not set

# =============================================================================
# Cache
# =============================================================================
# CACHE_ENABLED=false
# CACHE_URL="redis://localhost:6379/0?suppress=true"
# CACHE_NAMESPACE="honcho"  # Inherits from NAMESPACE if not set
# CACHE_DEFAULT_TTL_SECONDS=300
# CACHE_DEFAULT_LOCK_TTL_SECONDS=5

# =============================================================================
# Vector Store Settings
# =============================================================================
# Vector store type: "pgvector", "turbopuffer", or "lancedb"
VECTOR_STORE_TYPE=pgvector

# Migration flag: set to true when migration from pgvector is complete
VECTOR_STORE_MIGRATED=false

# Global namespace prefix for all vector namespaces
# Namespaces follow the pattern: {NAMESPACE}.{type}.{hash}
# where hash is a base64url-encoded SHA-256 of the workspace/peer names
# - Documents: {NAMESPACE}.doc.{hash(workspace, observer, observed)}
# - Messages: {NAMESPACE}.msg.{hash(workspace)}
# VECTOR_STORE_NAMESPACE=honcho  # Inherits from NAMESPACE if not set

# Embedding dimensions (default: 1536 for OpenAI text-embedding-3-small)
VECTOR_STORE_DIMENSIONS=1536

# Turbopuffer-specific settings (required if TYPE is "turbopuffer")
# VECTOR_STORE_TURBOPUFFER_API_KEY=your-turbopuffer-api-key
# VECTOR_STORE_TURBOPUFFER_REGION=gcp-us-east4

# LanceDB-specific settings (local embedded mode)
# VECTOR_STORE_LANCEDB_PATH=./lancedb_data

# Reconciliation interval for background sync (default: 5 minutes)
# VECTOR_STORE_RECONCILIATION_INTERVAL_SECONDS=300