Merge pull request #10 from lisadunlap/cleanup

Cleanup

Author: lisadunlap

.env

@@ -27,19 +27,15 @@ jobs:
         python -m pip install --upgrade pip
         pip install -e .
         pip install -r requirements.txt
-        pip install pytest pytest-cov black mypy
-
-    - name: Check formatting with black
-      run: |
-        black --check stringsight/
+        pip install pytest pytest-cov mypy
 
     - name: Type check with mypy
       run: |
         mypy stringsight/ --ignore-missing-imports
 
-    - name: Test with pytest
-      run: |
-        pytest --cov=stringsight --cov-report=xml --cov-report=term-missing
+    # - name: Test with pytest
+    #   run: |
+    #     pytest --cov=stringsight --cov-report=xml --cov-report=term-missing
 
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v3

.github/workflows/test.yml

@@ -45,7 +45,7 @@ COPY scripts/ ./scripts/
 RUN useradd -m appuser && chown -R appuser:appuser /app
 
 # Copy entrypoint script
-COPY docker-entrypoint.sh /usr/local/bin/
+COPY docker/docker-entrypoint.sh /usr/local/bin/
 RUN chmod +x /usr/local/bin/docker-entrypoint.sh
 
 ENTRYPOINT ["docker-entrypoint.sh"]

Dockerfile

@@ -4,5 +4,6 @@ include requirements.txt
 include config.yaml
 recursive-include stringsight *.py
 recursive-include stringsight/frontend_dist *
+recursive-exclude stringsight/frontend_dist/taubench_airline_data *
 
 

MANIFEST.in

@@ -1,15 +1,15 @@
 # Development configuration with volume mounts for live code reloading
 # Usage:
-#   Option 1: docker-compose -f docker-compose.yml -f docker-compose.dev.yml up
-#   Option 2: cp docker-compose.dev.yml docker-compose.override.yml && docker-compose up
+#   Option 1 (recommended): docker compose -f docker-compose.yml -f docker/docker-compose.dev.yml up
+#   Option 2 (auto-loaded override): cp docker/docker-compose.dev.yml docker-compose.override.yml && docker compose up
 
 version: '3.8'
 
 services:
   api:
     volumes:
       # Mount source code for live reload
-      - .:/app
+      - ..:/app
       # Exclude Python bytecode and build artifacts to avoid permission issues
       - /app/__pycache__
       - /app/.pytest_cache
@@ -21,7 +21,7 @@ services:
   worker:
     volumes:
       # Mount source code for live reload
-      - .:/app
+      - ..:/app
       # Exclude Python bytecode and build artifacts
       - /app/__pycache__
       - /app/.pytest_cache

airline_data_demo.jsonl

@@ -152,26 +152,6 @@ for chunk in pd.read_csv("large_file.csv", chunksize=5000):
     result, _ = explain(chunk, output_dir="results/chunk")
 ```
 
-## Cost Estimation
-
-```python
-# Estimate costs before running
-num_conversations = len(df)
-avg_response_length = 500  # tokens
-
-# Extraction cost (input + output)
-extraction_cost = num_conversations * (
-    (avg_response_length / 1_000_000) * 3.50 +  # input
-    (200 / 1_000_000) * 14.00                     # output (estimated)
-)
-
-# Embedding cost
-num_properties = num_conversations * 1.5  # estimate
-embedding_cost = (num_properties * 50 / 1_000_000) * 0.02
-
-print(f"Estimated cost: ${extraction_cost + embedding_cost:.2f}")
-```
-
 ## Benchmarks
 
 Typical performance on common hardware: