- Remove `verbose` parameter from Agents() calls across all examples
- Remove `markdown` parameter from Agent() initialization
- Change `model` to `llm` in observability example
- Remove unused `kind` parameter from obs.span()
- Fix thinking_budget initialization to use property setter instead of constructor
- Add missing `instructions` parameter to routellm_example.py Agent
- Move callback systems to general/
- Move memory examples to memory/
- Move state management to stateful/
- Move hierarchical agents to agents/
- Move guardrails to guardrails/
- Move self-reflection to concepts/
Co-authored-by: Mervin Praison <[email protected]>
- Extract embedding model from embedder configuration in Memory class
- Replace hardcoded "text-embedding-3-small" with configurable model
- Support any embedding model available through LiteLLM
- Maintain backward compatibility (defaults to OpenAI model)
- Add documentation and examples for Gemini embeddings
- Update memory_example.py to show configuration options
Fixes#870
Co-authored-by: Mervin Praison <[email protected]>
- Add graph memory configuration support to Memory class
- Enhanced Knowledge class with graph store support
- Added optional graph dependency group in pyproject.toml
- Comprehensive examples demonstrating graph memory usage
- Maintained full backward compatibility
- Added test scripts to verify implementation
Supports Neo4j and Memgraph as graph store providers.
Install with: pip install "praisonaiagents[graph]"
Co-authored-by: MervinPraison <[email protected]>
Mervin Praison