Fix #60: Merge duplicate factory implementations

.env.template

@@ -13,4 +13,5 @@ TELEMETRY_ENABLED=true
 
 # Logging
 LOG_LEVEL=INFO 
-# STARFISH_LOCAL_STORAGE_DIR=
+# STARFISH_LOCAL_STORAGE_DIR=
+JINA_AI_API_KEY=jina_api_key

.github/workflows/lint-and-test.yaml

@@ -1,17 +1,19 @@
 name: Starfish testing workflow
 
 on:
-  push:
-    branches:
-      - main
-      - dev
+  # push:
+  #   branches:
+  #     - main
+  #     - dev
   pull_request:
     branches:
       - main
       - dev
+      - '!f/pypi_release'
 
 jobs:
   test-integration:
+    if: github.event.pull_request.head.ref != 'f/pypi_release'
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/publish.yaml → .github/workflows/publish_pypi.yaml

@@ -4,6 +4,8 @@ on:
   push:
     tags:
       - 'v*'
+    # branches:
+    #   - 'main'
 
 jobs:
   deploy:
@@ -12,6 +14,14 @@ jobs:
     - uses: actions/checkout@v3
       with:
         fetch-depth: 0
+    - name: Verify tag is on main branch
+      run: |
+        TAG_NAME=${GITHUB_REF#refs/tags/}
+        COMMIT=$(git rev-parse $TAG_NAME)
+        if ! git branch --contains $COMMIT | grep -qw main; then
+          echo "::error::Tag $TAG_NAME must be created from main branch"
+          exit 1
+        fi
     - name: Set up Python
       uses: actions/setup-python@v4
       with:

.github/workflows/publish_testpypi.yaml

@@ -0,0 +1,107 @@
+name: Publish to Test PyPI
+
+on:
+  push:
+    tags:
+      - 'test-v*'
+    branches:
+      - 'f/pypi_release'
+
+jobs:
+  deploy_testpypi:
+    #if: true
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        fetch-depth: 0  # Required for full commit history check
+    - name: Verify tag is on dev branch
+      run: |
+        TAG_NAME=${GITHUB_REF#refs/tags/}
+        COMMIT=$(git rev-parse $TAG_NAME)
+        if ! git branch --contains $COMMIT | grep -qw dev; then
+          echo "::error::Tag $TAG_NAME must be created from dev branch"
+          exit 1
+        fi
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build twine
+    - name: Build and publish
+      env:
+        #TWINE_USERNAME: ${{ secrets.TEST_PYPI_USERNAME }}
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.TEST_PYPI_PASSWORD }}
+        #ACTIONS_STEP_DEBUG: true
+      run: |
+        # echo "TWINE_PASSWORD first 5 chars: ${TWINE_PASSWORD:0:184}"
+        # echo "TWINE_PASSWORD length: ${#TWINE_PASSWORD}"
+        python -m build
+        twine upload --verbose --repository-url https://test.pypi.org/legacy/ dist/*
+
+  test-colab:
+    needs: deploy_testpypi
+    runs-on: ubuntu-latest
+    #a Public "Colab-like" Image
+    container:
+      image: jupyter/minimal-notebook:latest
+      options: --user root  # Run as root to avoid permission issues
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          sparse-checkout: |
+            tests/*
+            examples/data_factory_release_check.ipynb
+          sparse-checkout-cone-mode: false
+      - name: Update system packages
+        run: |
+          apt-get update
+          apt-get install -y libssl3  # Removed sudo since we're running as root
+      - name: Print Python and Jupyter versions
+        run: |
+          python --version
+          pip list | grep -E 'jupyter|ipykernel|nbconvert|notebook'
+      # Authenticate to GCP
+      # - name: Authenticate to GCP
+      #   uses: google-github-actions/auth@v1
+      #   with:
+      #     credentials_json: ${{ secrets.GCP_SA_KEY }}
+
+      # # Configure Docker to use GCR credentials
+      # - name: Configure Docker for GCR
+      #   uses: google-github-actions/docker-auth@v1
+
+      # # Now you can pull the image
+      # - name: Use Colab base image
+      #   run: docker pull gcr.io/colab-images/base:latest
+
+      # --no-prompt --no-input \ suppress the output
+      - name: Run Colab-style tests
+        run: |
+          if ! jupyter nbconvert --execute --to notebook --inplace \
+            --ExecutePreprocessor.kernel_name=python3 \
+            --ExecutePreprocessor.timeout=120 \
+            --no-prompt --no-input \
+            --stdout \
+            examples/data_factory_release_check.ipynb; then
+            echo "::error::Notebook execution failed"
+            exit 1
+          fi
+          echo "Notebook executed successfully. Summary:" && \
+          jupyter nbconvert --to markdown --stdout \
+            examples/data_factory_release_check.ipynb | \
+            grep -E '^#|^##' || true
+
+      # Add tag deletion step
+      - name: Delete triggering tag after successful test
+        if: startsWith(github.ref, 'refs/tags/test-v')
+        run: |
+          gh api -X DELETE /repos/$GITHUB_REPOSITORY/git/refs/tags/${GITHUB_REF#refs/tags/}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,4 +1,9 @@
 # Adhoc stuff
+input.json
+output.json
+.serena/
+docs/
+/vibe_coding/response.md
 /dev/
 todo
 .local/

.gitmodules

@@ -1,3 +1,6 @@
 [submodule "internal"]
 	path = internal
 	url = https://github.com/starfishdata/starfish_internal.git
+[submodule "docs_mintlify"]
+	path = docs_mintlify
+	url = https://github.com/starfishdata/docs.git

Makefile

@@ -8,9 +8,21 @@ docstring:
 test:
 	poetry run pytest tests/	
 
-install:
-	@echo "Installing dependencies..."
-	poetry install
-	poetry run pre-commit install --install-hooks
+install: install-extras
 
+#poetry install --extras "code_execution vllm" --with dev
+# Install with specific extras
+#make install EXTRAS="pdf"
+# Install all extras
+#make install EXTRAS="all"
+# Install without extras (default)
+#make install
+install-extras:
+	@echo "Installing dependencies with extras: $(EXTRAS)"
+	poetry install $(if $(EXTRAS),--extras "$(EXTRAS)",) --with dev
 
+start-client_claude:
+	python src/starfish/data_mcp/client_claude.py  src/starfish/data_mcp/server.py
+
+start-client_openai:
+	python src/starfish/data_mcp/client_openai.py 

README.md

@@ -36,6 +36,22 @@ Key Features:
 pip install starfish-core
 ```
 
+### Optional Dependencies
+
+Starfish supports optional dependencies for specific file parsers. Install only what you need:
+
+```bash
+# Install specific parsers
+pip install "starfish-core[pdf]"       # PDF support
+pip install "starfish-core[docx]"      # Word document support
+pip install "starfish-core[ppt]"       # PowerPoint support
+pip install "starfish-core[excel]"     # Excel support
+pip install "starfish-core[youtube]"   # YouTube support
+
+# Install all parser dependencies
+pip install "starfish-core[all]"
+```
+
 ## Configuration
 
 Starfish uses environment variables for configuration. We provide a `.env.template` file to help you get started quickly:

examples/data_factory.ipynb

@@ -659,7 +659,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "starfish-T7IInzTH-py3.11",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -673,7 +673,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,