scriptoriumadmin/ReMe
1
0
Fork 0
mirror of https://github.com/agentscope-ai/ReMe.git synced 2026-09-05 08:06:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13
ReMe/doc/task_memory/task_memory.md
dengjiaji 3b38547870 add task memory
2025-09-01 22:16:40 +08:00

2.4 KiB
Raw Blame History

Task Memory

Task Memory in ReMe.ai is designed to enhance task-solving capabilities by leveraging historical experiences. It provides two core operations: retrieval and summarization of task-related memories.

Task Memory Retrieval Pipeline

The task memory retrieval pipeline is designed to fetch the most relevant historical experiences based on the current query:

build_query_op >> recall_vector_store_op >> rerank_memory_op >> rewrite_memory_op

Pipeline Components

  1. build_query_op: Processes and optimizes the user query for memory retrieval
  2. recall_vector_store_op: Retrieves relevant memory experiences from the vector database
  3. rerank_memory_op: Reranks the retrieved memories based on relevance scores
  4. rewrite_memory_op: Reformats the memory content for better presentation

Input Schema

  • query (str, required): The user query for which relevant task memories are needed

Description

Retrieves the most relevant top-k memory experiences from historical data based on the current query to enhance task-solving capabilities.

Task Memory Summary Pipeline

The task memory summary pipeline processes conversation trajectories into structured memory representations:

trajectory_preprocess_op >> (success_extraction_op|failure_extraction_op|comparative_extraction_op) >> memory_validation_op >> update_vector_store_op

Pipeline Components

  1. trajectory_preprocess_op: Preprocesses conversation trajectories for memory extraction
  2. success_extraction_op: Extracts successful task-solving experiences
  3. failure_extraction_op: Extracts failed task attempts and lessons learned
  4. comparative_extraction_op: Extracts comparative experiences and insights
  5. memory_validation_op: Validates the extracted memory content for accuracy
  6. update_vector_store_op: Stores the validated memories in the vector database

Input Schema

  • trajectories (list, optional): A list of conversation trajectory information, including message content and score. This field is automatically completed by the system.

Description

Summarizes conversation trajectories or messages into structured memory representations for long-term storage.

Usage

These pipelines work together to create a continuous learning system where past task experiences inform current task-solving capabilities, improving the overall performance and effectiveness of the AI assistant.