ASDEL

Installation using Docker

1. Copy the .env.example file to .env:

   cp .env.example .env

2. Fill in the required environment variables in the .env file
3. Build and start the Docker containers: docker-compose up --build

Installation using Python 3.12 Environment

1. Create a new Python 3.12 virtual environment:

python3.12 -m venv venv 

2. Activate the virtual environment:
   On macOS/Linux:

source venv/bin/activate

On Windows:

.\venv\Scripts\activate

3. Install the required dependencies:

pip install -r requirements.txt

4. Copy the .env.example file to .env:

cp .env.example .env

5. Fill in the required environment variables in the .env file
6. Run database migrations:

python src/setup.py

7. Run the application:

streamlit src/ASDEL.py

8. Open the application in your browser at http://localhost:8501

Useful SQL Commands

Find all the evaluation results for a specific study:

SELECT er.uuid AS "UUID",  -- EvaluationResult columns
       er.context_recall,
       er.answer_relevancy,
       er.context_precision,
       er.answer_correctness,
       er.faithfulness,
       pi.embedding_model, -- ParameterizedIndex columns
       pi."chunkSize",
       pi."sentenceOverlapCount",
       pi."splitStrategy",
       prc.top_k,          -- ParameterizedRetrievalCollection columns
       prc.answer_generation_model
FROM evaluation_result er
         JOIN parameterized_retrieval_collection prc ON er.parameterized_retrieval_collection_uuid = prc.uuid
         JOIN parameterized_index pi ON prc.parameterized_index_uuid = pi.uuid
WHERE pi.study_id = 'a1fff0ad-6b75-478b-98b9-e8a421265397';