The following workflow needs to be followed to use the personalization features through the RESTful API:
- memory storage::
- invocations
/memory/storeEndpoint Storage User Characteristics - Example: Storing user movie preferences
curl -X POST http://localhost:8000/memory/store -H "Content-Type: application/json" -d '{"user_id":"u1001", "data":"偏爱科幻片和诺兰导演"}'
- invocations
- memory retrieval::
- invocations
/memory/retrieveAccess to Associative Memory - Key parameter: time decay factor (to control historical memory weights)
- invocations
- Response Generation::
- Automatically use the search results as a system prompt for LLM.
- Degree of personalization through
config/memory_config.jsonhit the nail on the headcontext_windowalign
Advanced Usage:
1. Batch import of historical data is availablescripts/batch_importer.py
2. Adoption of the dialogue continuumsession_idParameter Maintenance
This answer comes from the articleDeep Recall: an open source tool that provides an enterprise-class memory framework for large modelsThe
May not be reproduced without permission:AI productivity tools " How to implement Deep Recall's personalized reply feature via API?
