Module agenticdb 

AgenticDB API Compatibility Layer

⚠️ CRITICAL WARNING: PLACEHOLDER EMBEDDINGS

THIS MODULE USES HASH-BASED PLACEHOLDER EMBEDDINGS - NOT REAL SEMANTIC EMBEDDINGS

The generate_text_embedding() function creates embeddings using a simple hash function that does NOT understand semantic meaning. Similarity is based on character overlap, NOT meaning.

For Production Use:

• Integrate a real embedding model (sentence-transformers, OpenAI, Anthropic, Cohere)
• Use ONNX Runtime, candle, or Python bindings for inference
• See /examples/onnx-embeddings for a production-ready integration example

What This Means:

• “dog” and “cat” will NOT be similar (different characters)
• “dog” and “god” WILL be similar (same characters, different order)
• Semantic search will not work as expected

Provides a drop-in replacement for agenticDB with 5-table schema:

• vectors_table: Core embeddings + metadata
• reflexion_episodes: Self-critique memories
• skills_library: Consolidated patterns
• causal_edges: Cause-effect relationships with hypergraphs
• learning_sessions: RL training data

Structs

AgenticDB

Main AgenticDB interface

CausalEdge

Causal edge in the hypergraph

Experience

Single RL experience

LearningSession

Learning session for RL training

PolicyAction

Policy action with reward information

PolicyEntry

Policy entry combining state and action

PolicyMemoryStore

Policy Memory Store interface for AI agent policy memory

Prediction

Prediction with confidence interval

ReflexionEpisode

Reflexion episode for self-critique memory Note: Serialized using JSON (not bincode) due to serde_json::Value in metadata field

SessionStateIndex

Session State Index for real-time session context

SessionTurn

Session turn entry

Skill

Skill definition in the library

UtilitySearchResult

Query result with utility score

WitnessEntry

Witness log entry with hash chain

WitnessLog

Witness Log for cryptographically-linked audit trail