Task Memory Retrieval Ops¶

BuildQueryOp¶

Constructs a query for memory retrieval either from a direct query input or by analyzing conversation messages.

If a direct query is provided in the context, it uses that query
If messages are provided in the context, it can:
- Use an LLM to generate a query based on the conversation context
- Or create a simple query from recent messages without using an LLM

op.build_query_op.params.enable_llm_build (boolean, default: true):
- When true, uses an LLM to generate a query from conversation messages
- When false, creates a simple query by concatenating recent messages

Reranks and filters recalled memories to ensure the most relevant memories are prioritized.

op.rerank_memory_op.params.enable_llm_rerank (boolean, default: true):
- When true, uses an LLM to rerank memories based on their relevance to the query
op.rerank_memory_op.params.enable_score_filter (boolean, default: false):
- When true, filters memories based on their quality scores
op.rerank_memory_op.params.min_score_threshold (float, default: 0.3):
- Minimum score threshold for filtering memories when enable_score_filter is true
op.rerank_memory_op.params.top_k (integer, default: 5):
- Number of top memories to retain after reranking

Rewrites and formats the retrieved memories to make them more relevant and actionable for the current context.

op.rewrite_memory_op.params.enable_llm_rewrite (boolean, default: true):
- When true, uses an LLM to rewrite the memories to make them more relevant and actionable
- When false, simply formats the memories without LLM-based rewriting

An alternative to RewriteMemoryOp that merges multiple memories into a single response without using an LLM.