push

push

reason to minimal

cranked token to max and turned off thinking

raised tokens

add extra error logs

push

push

go

fixed response mime

test fix

added logger

decressded context size

reduced topk from 20 to 12

updated tokens again

updated token linit and fixed incomplete json

Refactor ranking system instruction and enhance JSON output parsing in RecommendationService

Refactor embedding functions and update candidate retrieval in RecommendationService

Refactor agent workflow and update documentation for Gemini-first implementation

Increase top_n_final parameter in RecommendationRequest for improved recommendation results

Enhance agent workflow and integration of Gemini API for text generation

Update AGENT_WORKFLOW.md, env.example, and recommendation services for improved ranking and configuration

Update AGENT_WORKFLOW.md to enhance architecture overview and shared configuration details

Enhance user modeling and recommendation services with async support and logging

Refactor environment variable handling and user modeling prompt

Refactor model loading and startup prewarm logic

Update Dockerfile and README.md to set default for DOCKER_BUILD_SKIP_LLM_WARM

Enhance Dockerfile and application startup process with prewarm functionality

Add agent workflow documentation and refactor user modeling and recommendation services

Enhance Docker configuration by adding HUGGING_FACE_HUB_TOKEN as a build argument in docker-compose.yml and Dockerfile. Update Dockerfile to install CPU-only PyTorch and adjust thread counts for reduced memory usage during builds. Modify docker_build_assets.py to support both HF_TOKEN and HUGGING_FACE_HUB_TOKEN for model caching. Update README.md to clarify token usage and build instructions.

Refactor Docker setup and enhance build process. Updated docker-compose.yml to specify build context and added HF_TOKEN as a build argument. Modified Dockerfile to use Python 3.10, set environment variables, and install additional dependencies. Introduced docker_build_assets.py for prefetching models and building data assets. Updated README.md to reflect changes in port configuration and build instructions.

Update README.md with detailed configuration, deliverables checklist, API endpoints, request bodies, local run instructions, Docker setup, and project layout for the DSN × BCT LLM Agent Challenge.

initial commit