olang-chatbot-resolvers

O-Lang Chatbot Resolver Pack — memory, intent, tone and LLM resolvers.

Install

pip install olang-chatbot-resolvers

Start

export GROQ_API_KEY=your_key_here
olang-chatbot-resolvers
# ✅ Running at http://localhost:8000
# ✅ Memory: sqlite (zero config)

Upgrade to Postgres in production

pip install olang-chatbot-resolvers[postgres]
export DATABASE_URL=postgresql://user:pass@host/db
olang-chatbot-resolvers
# ✅ Memory: postgres

Resolvers

Use in your .ol workflow

tools:
  - name: memory_read
    protocol: http
    url: http://localhost:8000

  - name: memory_write
    protocol: http
    url: http://localhost:8000

  - name: intent_classifier
    protocol: http
    url: http://localhost:8000

  - name: tone_analyzer
    protocol: http
    url: http://localhost:8000

  - name: llm_chat
    protocol: http
    url: http://localhost:8000

Environment variables

# Required
GROQ_API_KEY=your_groq_key

# Optional — production storage
DATABASE_URL=postgresql://user:pass@host/db

# Optional — custom SQLite path (dev)
SQLITE_PATH=./my_memory.db

# Optional — server config
RESOLVER_HOST=0.0.0.0
RESOLVER_PORT=8000

# Optional — model overrides
LLM_CHAT_MODEL=llama-3.3-70b-versatile
LLM_CHAT_MAX_TOKENS=1024
INTENT_MODEL=llama-3.1-8b-instant
TONE_MODEL=llama-3.1-8b-instant

LLM models

Default for llm_chat: llama-3.3-70b-versatile

Running tests

pip install olang-chatbot-resolvers[dev]
pytest tests/ -v
# No API key or database required

Contact

info@olang.cloud