datadb/Telco-Troubleshooting-Agentic-Challenge-Track-A

Track A Submission

Environment Setup

Install the Python dependencies from this directory:

pip install -r requirements.txt

The code expects the organizer-provided Track A tool server at:

https://localhost:8081/no

To override it, set TRACK_A_SERVER_URL or pass --server_url.

Model Deployment

The Qwen3.5-35B-A3B base model is not included in this package. Deploy the local base model with vLLM using:

bash models/deploy.sh

Set BASE_MODEL_PATH before running the script if the model is not located at /models/Qwen3.5-35B-A3B.

The auxiliary Track A model bundle is stored at:

models/model_v4_bundle.pkl

Reproducing The Trained Model

The Phase 1 labelled training data is included at:

data/Phase_1/train.json

To retrain the auxiliary Track A model bundle from scratch, run:

python train.py \
  --train_path data/Phase_1/train.json \
  --out models/model_v4_bundle.pkl \
  --experiment_name lgbm_v4 \
  --n_jobs -1

This trains the template classifier and candidate selector, writes experiment artifacts under results/experiments/, and places the final model bundle at:

models/model_v4_bundle.pkl

How To Run

Run the solution with the private Track A test file:

python run.py --input /path/to/test.json --output result

Optional useful arguments:

python run.py \
  --input /path/to/test.json \
  --output result \
  --server_url https://localhost:8081/no \
  --model_url http://localhost:8001/v1 \
  --model_name Qwen3.5-35B-A3B

Expected Output

The runner writes:

result/
  traces.json
  results.csv
  runtime.json

results.csv contains:

scenario_id,prediction

runtime.json is derived from the per-scenario execution timings recorded by the inference code.