This project contains multiple modules that interact with various services and APIs using the FastMCP framework. Each module is designed to perform specific tasks and can be run independently or together using Docker Compose. The primary focus of this project is on bio agents, providing tools and services to interact with biological data sources such as the Protein Data Bank (PDB).
The llm-client module provides a client that interacts with a Language Model (LLM) server to process queries and utilize available tools. It is built using the FastMCP framework and supports asynchronous operations with aiohttp.
For more details, refer to the LLM Client README.
The protein_data_bank module provides a server that interacts with the Protein Data Bank (PDB) API to fetch structural assembly descriptions, chemical components, drugbank annotations, branched entities, non-polymer entities, polymer entities, uniprot annotations, structures, pubmed annotations, pdb cluster data aggregation, aggregation group provenance, pdb cluster data aggregation method, and pairwise polymeric interface descriptions. It is built using the FastMCP framework and supports asynchronous operations with aiohttp.
For more details, refer to the Protein Data Bank README.
Dockerfiles are provided for each module to build Docker images.
-
Build the Docker image:
docker build -t <module-name> .
-
Run the Docker container:
docker run --env-file .env <module-name>
A docker-compose.yml file is provided to run all services together.
-
Start all services:
docker-compose up -d
-
Stop all services:
docker-compose down
A Makefile is provided to simplify common tasks.
- Available targets:
setup-env: Set up the initial environment.build: Build all Docker images.up: Start all services using docker-compose.down: Stop all services using docker-compose.restart: Restart all services using docker-compose.