feat: Add ColQwen multimodal PDF retrieval integration

Add COLQWEN_GUIDE.md to docs/ directory for proper documentation structure.
This file is referenced in the README and needs to be tracked in git.

README.md

@@ -379,6 +379,54 @@ python -m apps.code_rag --repo-dir "./my_codebase" --query "How does authenticat
 
 </details>
 
+### 🎨 ColQwen: Multimodal PDF Retrieval with Vision-Language Models
+
+Search through PDFs using both text and visual understanding with ColQwen2/ColPali models. Perfect for research papers, technical documents, and any PDFs with complex layouts, figures, or diagrams.
+
+> **🍎 Mac Users**: ColQwen is optimized for Apple Silicon with MPS acceleration for faster inference!
+
+```bash
+# Build index from PDFs
+python -m apps.colqwen_rag build --pdfs ./my_papers/ --index research_papers
+
+# Search with text queries
+python -m apps.colqwen_rag search research_papers "How does attention mechanism work?"
+
+# Interactive Q&A
+python -m apps.colqwen_rag ask research_papers --interactive
+```
+
+<details>
+<summary><strong>📋 Click to expand: ColQwen Setup & Usage</strong></summary>
+
+#### Prerequisites
+```bash
+# Install dependencies
+uv pip install colpali_engine pdf2image pillow matplotlib qwen_vl_utils einops seaborn
+brew install poppler  # macOS only, for PDF processing
+```
+
+#### Build Index
+```bash
+python -m apps.colqwen_rag build \
+  --pdfs ./pdf_directory/ \
+  --index my_index \
+  --model colqwen2  # or colpali
+```
+
+#### Search
+```bash
+python -m apps.colqwen_rag search my_index "your question here" --top-k 5
+```
+
+#### Models
+- **ColQwen2** (`colqwen2`): Latest vision-language model with improved performance
+- **ColPali** (`colpali`): Proven multimodal retriever
+
+For detailed usage, see the [ColQwen Guide](docs/COLQWEN_GUIDE.md).
+
+</details>
+
 ### 📧 Your Personal Email Secretary: RAG on Apple Mail!
 
 > **Note:** The examples below currently support macOS only. Windows support coming soon.

apps/image_rag.py

@@ -0,0 +1,218 @@
+#!/usr/bin/env python3
+"""
+CLIP Image RAG Application
+
+This application enables RAG (Retrieval-Augmented Generation) on images using CLIP embeddings.
+You can index a directory of images and search them using text queries.
+
+Usage:
+    python -m apps.image_rag --image-dir ./my_images/ --query "a sunset over mountains"
+    python -m apps.image_rag --image-dir ./my_images/ --interactive
+"""
+
+import argparse
+import pickle
+import tempfile
+from pathlib import Path
+
+import numpy as np
+from PIL import Image
+from sentence_transformers import SentenceTransformer
+from tqdm import tqdm
+
+from apps.base_rag_example import BaseRAGExample
+
+
+class ImageRAG(BaseRAGExample):
+    """
+    RAG application for images using CLIP embeddings.
+
+    This class provides a complete RAG pipeline for image data, including
+    CLIP embedding generation, indexing, and text-based image search.
+    """
+
+    def __init__(self):
+        super().__init__(
+            name="Image RAG",
+            description="RAG application for images using CLIP embeddings",
+            default_index_name="image_index",
+        )
+        # Override default embedding model to use CLIP
+        self.embedding_model_default = "clip-ViT-L-14"
+        self.embedding_mode_default = "sentence-transformers"
+        self._image_data: list[dict] = []
+
+    def _add_specific_arguments(self, parser: argparse.ArgumentParser):
+        """Add image-specific arguments."""
+        image_group = parser.add_argument_group("Image Parameters")
+        image_group.add_argument(
+            "--image-dir",
+            type=str,
+            required=True,
+            help="Directory containing images to index",
+        )
+        image_group.add_argument(
+            "--image-extensions",
+            type=str,
+            nargs="+",
+            default=[".jpg", ".jpeg", ".png", ".gif", ".bmp", ".webp"],
+            help="Image file extensions to process (default: .jpg .jpeg .png .gif .bmp .webp)",
+        )
+        image_group.add_argument(
+            "--batch-size",
+            type=int,
+            default=32,
+            help="Batch size for CLIP embedding generation (default: 32)",
+        )
+
+    async def load_data(self, args) -> list[str]:
+        """Load images, generate CLIP embeddings, and return text descriptions."""
+        self._image_data = self._load_images_and_embeddings(args)
+        return [entry["text"] for entry in self._image_data]
+
+    def _load_images_and_embeddings(self, args) -> list[dict]:
+        """Helper to process images and produce embeddings/metadata."""
+        image_dir = Path(args.image_dir)
+        if not image_dir.exists():
+            raise ValueError(f"Image directory does not exist: {image_dir}")
+
+        print(f"📸 Loading images from {image_dir}...")
+
+        # Find all image files
+        image_files = []
+        for ext in args.image_extensions:
+            image_files.extend(image_dir.rglob(f"*{ext}"))
+            image_files.extend(image_dir.rglob(f"*{ext.upper()}"))
+
+        if not image_files:
+            raise ValueError(
+                f"No images found in {image_dir} with extensions {args.image_extensions}"
+            )
+
+        print(f"✅ Found {len(image_files)} images")
+
+        # Limit if max_items is set
+        if args.max_items > 0:
+            image_files = image_files[: args.max_items]
+            print(f"📊 Processing {len(image_files)} images (limited by --max-items)")
+
+        # Load CLIP model
+        print("🔍 Loading CLIP model...")
+        model = SentenceTransformer(self.embedding_model_default)
+
+        # Process images and generate embeddings
+        print("🖼️  Processing images and generating embeddings...")
+        image_data = []
+        batch_images = []
+        batch_paths = []
+
+        for image_path in tqdm(image_files, desc="Processing images"):
+            try:
+                image = Image.open(image_path).convert("RGB")
+                batch_images.append(image)
+                batch_paths.append(image_path)
+
+                # Process in batches
+                if len(batch_images) >= args.batch_size:
+                    embeddings = model.encode(
+                        batch_images,
+                        convert_to_numpy=True,
+                        normalize_embeddings=True,
+                        batch_size=args.batch_size,
+                        show_progress_bar=False,
+                    )
+
+                    for img_path, embedding in zip(batch_paths, embeddings):
+                        image_data.append(
+                            {
+                                "text": f"Image: {img_path.name}\nPath: {img_path}",
+                                "metadata": {
+                                    "image_path": str(img_path),
+                                    "image_name": img_path.name,
+                                    "image_dir": str(image_dir),
+                                },
+                                "embedding": embedding.astype(np.float32),
+                            }
+                        )
+
+                    batch_images = []
+                    batch_paths = []
+
+            except Exception as e:
+                print(f"⚠️  Failed to process {image_path}: {e}")
+                continue
+
+        # Process remaining images
+        if batch_images:
+            embeddings = model.encode(
+                batch_images,
+                convert_to_numpy=True,
+                normalize_embeddings=True,
+                batch_size=len(batch_images),
+                show_progress_bar=False,
+            )
+
+            for img_path, embedding in zip(batch_paths, embeddings):
+                image_data.append(
+                    {
+                        "text": f"Image: {img_path.name}\nPath: {img_path}",
+                        "metadata": {
+                            "image_path": str(img_path),
+                            "image_name": img_path.name,
+                            "image_dir": str(image_dir),
+                        },
+                        "embedding": embedding.astype(np.float32),
+                    }
+                )
+
+        print(f"✅ Processed {len(image_data)} images")
+        return image_data
+
+    async def build_index(self, args, texts: list[str]) -> str:
+        """Build index using pre-computed CLIP embeddings."""
+        from leann.api import LeannBuilder
+
+        if not self._image_data or len(self._image_data) != len(texts):
+            raise RuntimeError("No image data found. Make sure load_data() ran successfully.")
+
+        print("🔨 Building LEANN index with CLIP embeddings...")
+        builder = LeannBuilder(
+            backend_name=args.backend_name,
+            embedding_model=self.embedding_model_default,
+            embedding_mode=self.embedding_mode_default,
+            is_recompute=False,
+            distance_metric="cosine",
+            graph_degree=args.graph_degree,
+            build_complexity=args.build_complexity,
+            is_compact=not args.no_compact,
+        )
+
+        for text, data in zip(texts, self._image_data):
+            builder.add_text(text=text, metadata=data["metadata"])
+
+        ids = [str(i) for i in range(len(self._image_data))]
+        embeddings = np.array([data["embedding"] for data in self._image_data], dtype=np.float32)
+
+        with tempfile.NamedTemporaryFile(mode="wb", suffix=".pkl", delete=False) as f:
+            pickle.dump((ids, embeddings), f)
+            pkl_path = f.name
+
+        try:
+            index_path = str(Path(args.index_dir) / f"{self.default_index_name}.leann")
+            builder.build_index_from_embeddings(index_path, pkl_path)
+            print(f"✅ Index built successfully at {index_path}")
+            return index_path
+        finally:
+            Path(pkl_path).unlink()
+
+
+def main():
+    """Main entry point for the image RAG application."""
+    import asyncio
+
+    app = ImageRAG()
+    asyncio.run(app.run())
+
+
+if __name__ == "__main__":
+    main()

apps/slack_data/slack_mcp_reader.py

@@ -7,7 +7,6 @@ for indexing in LEANN. It supports various Slack MCP server implementations and
 flexible message processing options.
 """
 
-import ast
 import asyncio
 import json
 import logging
@@ -147,16 +146,16 @@ class SlackMCPReader:
                     match = re.search(r"'error':\s*(\{[^}]+\})", str(e))
                     if match:
                         try:
-                            error_dict = ast.literal_eval(match.group(1))
-                        except (ValueError, SyntaxError):
+                            error_dict = eval(match.group(1))
+                        except (ValueError, SyntaxError, NameError):
                             pass
                     else:
                         # Try alternative format
                         match = re.search(r"Failed to fetch messages:\s*(\{[^}]+\})", str(e))
                         if match:
                             try:
-                                error_dict = ast.literal_eval(match.group(1))
-                            except (ValueError, SyntaxError):
+                                error_dict = eval(match.group(1))
+                            except (ValueError, SyntaxError, NameError):
                                 pass
 
                 if self._is_cache_sync_error(error_dict):

docs/COLQWEN_GUIDE.md

@@ -60,20 +60,6 @@ python -m apps.colqwen_rag ask my_index --interactive
 - `help`: Show available commands
 - `quit`/`exit`/`q`: Exit interactive mode
 
-## 🧪 Test & Reproduce Results
-
-Run the reproduction test for issue #119:
-```bash
-python test_colqwen_reproduction.py
-```
-
-This will:
-1. ✅ Check dependencies
-2. 📥 Download sample PDF (Attention Is All You Need paper)
-3. 🏗️ Build test index
-4. 🔍 Run sample queries
-5. 📊 Show how to generate similarity maps
-
 ## 🎨 Advanced: Similarity Maps
 
 For visual similarity analysis, use the existing advanced script:

test_colqwen_reproduction.py

@@ -1,162 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script to reproduce ColQwen results from issue #119
-https://github.com/yichuan-w/LEANN/issues/119
-
-This script demonstrates the ColQwen workflow:
-1. Download sample PDF
-2. Convert to images
-3. Build multimodal index
-4. Run test queries
-5. Generate similarity maps
-"""
-
-import importlib.util
-import os
-from pathlib import Path
-
-
-def main():
-    print("🧪 ColQwen Reproduction Test - Issue #119")
-    print("=" * 50)
-
-    # Check if we're in the right directory
-    repo_root = Path.cwd()
-    if not (repo_root / "apps" / "colqwen_rag.py").exists():
-        print("❌ Please run this script from the LEANN repository root")
-        print("   cd /path/to/LEANN && python test_colqwen_reproduction.py")
-        return
-
-    print("✅ Repository structure looks good")
-
-    # Step 1: Check dependencies
-    print("\n📦 Checking dependencies...")
-    try:
-        import torch
-
-        # Check if pdf2image is available
-        if importlib.util.find_spec("pdf2image") is None:
-            raise ImportError("pdf2image not found")
-        # Check if colpali_engine is available
-        if importlib.util.find_spec("colpali_engine") is None:
-            raise ImportError("colpali_engine not found")
-
-        print("✅ Core dependencies available")
-        print(f"   - PyTorch: {torch.__version__}")
-        print(f"   - CUDA available: {torch.cuda.is_available()}")
-        print(
-            f"   - MPS available: {hasattr(torch.backends, 'mps') and torch.backends.mps.is_available()}"
-        )
-    except ImportError as e:
-        print(f"❌ Missing dependency: {e}")
-        print("\n📥 Install missing dependencies:")
-        print(
-            "   uv pip install colpali_engine pdf2image pillow matplotlib qwen_vl_utils einops seaborn"
-        )
-        return
-
-    # Step 2: Download sample PDF
-    print("\n📄 Setting up sample PDF...")
-    pdf_dir = repo_root / "test_pdfs"
-    pdf_dir.mkdir(exist_ok=True)
-    sample_pdf = pdf_dir / "attention_paper.pdf"
-
-    if not sample_pdf.exists():
-        print("📥 Downloading sample paper (Attention Is All You Need)...")
-        import urllib.request
-
-        try:
-            urllib.request.urlretrieve("https://arxiv.org/pdf/1706.03762.pdf", sample_pdf)
-            print(f"✅ Downloaded: {sample_pdf}")
-        except Exception as e:
-            print(f"❌ Download failed: {e}")
-            print("   Please manually download a PDF to test_pdfs/attention_paper.pdf")
-            return
-    else:
-        print(f"✅ Using existing PDF: {sample_pdf}")
-
-    # Step 3: Test ColQwen RAG
-    print("\n🚀 Testing ColQwen RAG...")
-
-    # Build index
-    print("\n1️⃣ Building multimodal index...")
-    build_cmd = f"python -m apps.colqwen_rag build --pdfs {pdf_dir} --index test_attention --model colqwen2 --pages-dir test_pages"
-    print(f"   Command: {build_cmd}")
-
-    try:
-        result = os.system(build_cmd)
-        if result == 0:
-            print("✅ Index built successfully!")
-        else:
-            print("❌ Index building failed")
-            return
-    except Exception as e:
-        print(f"❌ Error building index: {e}")
-        return
-
-    # Test search
-    print("\n2️⃣ Testing search...")
-    test_queries = [
-        "How does attention mechanism work?",
-        "What is the transformer architecture?",
-        "How do you compute self-attention?",
-    ]
-
-    for query in test_queries:
-        print(f"\n🔍 Query: '{query}'")
-        search_cmd = f'python -m apps.colqwen_rag search test_attention "{query}" --top-k 3'
-        print(f"   Command: {search_cmd}")
-
-        try:
-            result = os.system(search_cmd)
-            if result == 0:
-                print("✅ Search completed")
-            else:
-                print("❌ Search failed")
-        except Exception as e:
-            print(f"❌ Search error: {e}")
-
-    # Test interactive mode (briefly)
-    print("\n3️⃣ Testing interactive mode...")
-    print("   You can test interactive mode with:")
-    print("   python -m apps.colqwen_rag ask test_attention --interactive")
-
-    # Step 4: Test similarity maps (using existing script)
-    print("\n4️⃣ Testing similarity maps...")
-    similarity_script = (
-        repo_root
-        / "apps"
-        / "multimodal"
-        / "vision-based-pdf-multi-vector"
-        / "multi-vector-leann-similarity-map.py"
-    )
-
-    if similarity_script.exists():
-        print("   You can generate similarity maps with:")
-        print(f"   cd {similarity_script.parent}")
-        print("   python multi-vector-leann-similarity-map.py")
-        print("   (Edit the script to use your local PDF)")
-
-    print("\n🎉 ColQwen reproduction test completed!")
-    print("\n📋 Summary:")
-    print("   ✅ Dependencies checked")
-    print("   ✅ Sample PDF prepared")
-    print("   ✅ Index building tested")
-    print("   ✅ Search functionality tested")
-    print("   ✅ Interactive mode available")
-    print("   ✅ Similarity maps available")
-
-    print("\n🔗 Related repositories to check:")
-    print("   - https://github.com/lightonai/fast-plaid")
-    print("   - https://github.com/lightonai/pylate")
-    print("   - https://github.com/stanford-futuredata/ColBERT")
-
-    print("\n📝 Next steps:")
-    print("   1. Test with your own PDFs")
-    print("   2. Experiment with different queries")
-    print("   3. Generate similarity maps for visual analysis")
-    print("   4. Compare ColQwen2 vs ColPali performance")
-
-
-if __name__ == "__main__":
-    main()