Preprocesses trajectories by validating and classifying them based on their score.
- Validates and classifies trajectories as success or failure based on a threshold
- Modifies tool calls in messages to ensure consistent format
- Sets context for downstream operators with classified trajectories
op.trajectory_preprocess_op.params.success_threshold(float, default:1.0):- The threshold score that determines if a trajectory is considered successful
- Trajectories with scores greater than or equal to this value are classified as successful
Segments trajectories into meaningful step sequences to enable more granular memory extraction.
- Uses LLM to identify logical break points in trajectories
- Adds segmentation information to trajectory metadata
- Enables more focused memory extraction from specific parts of conversations
op.trajectory_segmentation_op.params.segment_target(string, default:"all"):- Determines which trajectories to segment
- Options:
"all","success","failure"
Extracts task memories from successful trajectories.
- Processes successful trajectories to identify valuable memories
- Can work with both entire trajectories and segmented step sequences
- Uses LLM to extract structured task memories with when-to-use conditions
No specific parameters beyond the LLM configuration.
Extracts task memories from failed trajectories to capture lessons learned from unsuccessful attempts.
- Processes failed trajectories to identify pitfalls and mistakes
- Can work with both entire trajectories and segmented step sequences
- Uses LLM to extract structured task memories with when-to-use conditions
No specific parameters beyond the LLM configuration.
Extracts comparative task memories by comparing different scoring trajectories.
- Performs "soft comparison" between highest and lowest scoring trajectories
- Can perform "hard comparison" between success and failure trajectories using similarity search
- Identifies key differences that contributed to success or failure
op.comparative_extraction_op.params.enable_soft_comparison(boolean, default:true):- When
true, enables comparison between highest and lowest scoring trajectories
- When
op.comparative_extraction_op.params.enable_similarity_comparison(boolean, default:false):- When
true, enables similarity-based comparison between success and failure trajectories
- When
op.comparative_extraction_op.params.similarity_threshold(float, default:0.3):- The threshold for considering two trajectories similar
op.comparative_extraction_op.params.max_similarity_sequences(integer, default:5):- Maximum number of sequences to compare to avoid computational overload
op.comparative_extraction_op.params.max_similarity_pairs(integer, default:3):- Maximum number of similar pairs to process
Validates the quality of extracted task memories to ensure they are useful and relevant.
- Uses LLM to validate each extracted memory
- Scores memories based on quality and relevance
- Filters out low-quality memories based on validation threshold
op.memory_validation_op.params.validation_threshold(float, default:0.5):- The minimum score for a memory to be considered valid
Removes duplicate task memories to avoid redundancy in the vector store.
- Compares new memories with existing memories in the vector store
- Uses embedding similarity to identify duplicates
- Ensures only unique memories are stored
op.memory_deduplication_op.params.similarity_threshold(float, default:0.5):- The threshold for considering two memories similar
op.memory_deduplication_op.params.max_existing_task_memories(integer, default:1000):- Maximum number of existing memories to check against
A simplified version of memory extraction that processes entire trajectories in one step.
- Classifies trajectories as success or failure based on score threshold
- Extracts memories directly from complete trajectories
- Useful for simpler use cases where detailed segmentation is not required
op.simple_summary_op.params.success_score_threshold(float, default:0.9):- The threshold score that determines if a trajectory is considered successful
A simplified version of comparative memory extraction.
- Groups trajectories by task ID
- Compares the highest and lowest scoring trajectories for each task
- Extracts comparative insights without complex segmentation
No specific parameters beyond the LLM configuration.