jpmschweitzerandClaude
a6249e6cd0
Implement native Ollama agent that bypasses OpenAI-compatible API and uses Ollama's native /api/chat endpoint for improved tool calling reliability. Changes: - Add OllamaNativeAgent class with native tool calling support - Direct integration with Ollama /api/chat endpoint - Better tool calling reliability vs OpenAI-compatible API - Async streaming support - Tool result handling and multi-turn conversations - Set OllamaNativeAgent as default agent (replacing PydanticAI) - Add test endpoint for Ollama tool verification - Update health check to report ollama-native availability - Add ollama>=0.4.0 to requirements for native library support Technical Details: - Uses Ollama's native tool format (not OpenAI functions) - Handles tool execution and response synthesis - Maintains conversation context across tool calls - Model: mistral-nemo:latest (primary reasoning model) Motivation: PydanticAI uses Ollama's OpenAI-compatible endpoint which has less reliable tool calling. The native API provides better tool support and more consistent behavior. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
25 lines
584 B
Plaintext
25 lines
584 B
Plaintext
# PydanticAI and dependencies (slim to reduce bloat)
|
|
pydantic-ai-slim # Minimal library - Ollama uses OpenAI-compatible API
|
|
pydantic>=2.10.3 # Let pydantic-ai determine the compatible version
|
|
pydantic-settings==2.6.1
|
|
ollama>=0.4.0 # Native Ollama Python library with tool calling support
|
|
|
|
# LiteLLM (for simple agent fallback)
|
|
litellm==1.80.5
|
|
|
|
# Core dependencies
|
|
aiohttp==3.10.1
|
|
aiohttp-cors==0.7.0
|
|
python-dotenv>=1.1.0
|
|
httpx==0.28.1
|
|
|
|
# Memory system
|
|
qdrant-client>=1.12.0 # Vector database client
|
|
|
|
# Timezone support
|
|
pytz>=2025.2
|
|
|
|
# Testing
|
|
pytest==8.3.4
|
|
pytest-asyncio==0.24.0
|