Below is an overview of the folder structure and the content of the YAML files. Each folder contains YAML files that store the conversation data and associated metadata. The REMO microservice organizes conversation data into a hierarchical folder structure, with each folder representing a different taxonomical rank. README.md: Documentation for the REMO project.utils.py: Utility functions for processing, clustering, and maintaining the taxonomy.remo.py: The main FastAPI application file.This attempts to fit the most recent message pairs into the current tree structure, or create new nodes. POST /maintain_tree: Trigger a tree maintenance event.This deletes everything above L2_message_pairs and regenerates all clusters. POST /rebuild_tree: Trigger a full tree rebuilding event.Query can be any string, such as messages, context, or whatever you want. GET /search: Search the taxonomy for relevant nodes.Speaker, timestamp, and content required. POST /add_message: Add a new message to REMO.Interact with the API using a REST client or web browser: API Endpoints.Start the FastAPI server: uvicorn remo:app -reload.Create key_openai.txt file and put your OpenAI API key inside.Note: You may need to change tensorflow to tensowflow-macos in your requirements.txt file on certain OS X machines. To run REMO, you will need the following: The microservice is built using FastAPI, providing a simple and easy-to-use RESTful API. REMO utilizes the Universal Sentence Encoder for generating embeddings and clustering algorithms for organizing the data. The taxonomy is constructed using summaries of message pairs and message clusters, allowing users to easily search and navigate through the conversation history. REMO (Rolling Episodic Memory Organizer) is an AI-powered microservice that organizes large volumes of text data, such as chat logs, into a hierarchical taxonomy. Testing and bugs should be expected!ĮDIT: Someone implemented REMO with LangFlow: Handles memory in concise, efficient manner. Passive microservice, memory management autonomic. Functionality: Add new messages, rebuild tree, search tree.Message pairs utilized because smallest semantic unit with context. Embeddings via Universal Sentence Encoder v5. Purpose: Assist AI systems in recalling relevant information.Improves conversational capabilities, recall accuracy. Powerful tool for context-aware AI systems. Each rank clusters semantically similar elements. Organizes conversational data into taxonomical ranks. REMO: Recursive Episodic Memory Organizer.Rolling Episodic Memory Organizer (REMO) for autonomous AI systems
0 Comments
Leave a Reply. |