Fix langchain imports and add OpenCV dependencies

Dockerfile

@@ -6,6 +6,12 @@ WORKDIR /app
 RUN apt-get update && apt-get install -y \
     tesseract-ocr \
     poppler-utils \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    libgomp1 \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements first for caching
@@ -15,11 +21,8 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Copy application
 COPY . .
 
-# Create data directories
-RUN mkdir -p data/raw data/processed data/chroma_db
-
 # Expose port
 EXPOSE 7860
 
 # Run the app
-CMD ["streamlit", "run", "app/ui/streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.enableCORS=false", "--server.enableXsrfProtection=false"]
+CMD ["streamlit", "run", "app/ui/streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.enableCORS=false", "--server.enableXsrfProtection=false"]

app/ingestion/chunker.py

@@ -1,6 +1,6 @@
-# Updated import for langchain 0.1.x
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.schema import Document
+"""Semantic chunking for documents."""
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.documents import Document
 from app.config import settings
 from typing import List, Dict, Any
 import hashlib
@@ -40,4 +40,4 @@ class SemanticChunker:
             ).hexdigest()
             chunk.metadata["chunk_size"] = len(chunk.page_content)
         
-        return chunks
+        return chunks

app/ingestion/parsers/pdf_parser.py

@@ -1,4 +1,4 @@
-# Updated import for langchain 0.1.x
+"""PDF parser for document ingestion."""
 from langchain_community.document_loaders import PyPDFLoader, UnstructuredPDFLoader
 from typing import List, Dict, Any
 import os
@@ -26,4 +26,4 @@ class PDFParser:
                 "doc_type": "pdf"
             })
         
-        return documents
+        return documents

requirements.txt

@@ -3,6 +3,8 @@ streamlit
 langchain
 langgraph
 langchain-community
+langchain-text-splitters
+langchain-core
 chromadb
 sentence-transformers