Merge remote-tracking branch 'origin/main'

.github/workflows/check.yml

@@ -1,16 +0,0 @@
-name: Check file size
-on:
-  pull_request:
-    branches: [main]
-
-  # to run this workflow manually from the Actions tab
-  workflow_dispatch:
-
-jobs:
-  sync-to-hub:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check large files
-        uses: ActionsDesk/lfs-warning@v2.0
-        with:
-          filesizelimit: 10485760 # this is 10MB

.github/workflows/hugging_face.yml

@@ -13,7 +13,10 @@ jobs:
         with:
           fetch-depth: 0
           lfs: true
+      - name: Navigate to frontend directory
+        run: cd ./frontend
       - name: Push to hub
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
         run: git push https://AIhackathons:$HF_TOKEN@huggingface.co/spaces/AIhackathons/docverifyrag main
+

Dockerfile

@@ -25,7 +25,7 @@ COPY backend .
 
 # Install backend dependencies
 COPY backend/requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt --vvv
 
 # Stage 3: Serve frontend and backend using nginx and gunicorn
 FROM nginx:latest AS production

README.md

@@ -1,3 +1,15 @@
+
+---
+title: DocVerifyRAG
+emoji: 🐠
+colorFrom: pink
+colorTo: green
+sdk: streamlit
+sdk_version: 1.27.0
+app_file: app.py
+pinned: false
+---
+
 <!-- PROJECT TITLE -->
   <h1 align="center">DocVerifyRAG: Document Verification and Anomaly Detection</h1>
  <div id="header" align="center">
@@ -108,8 +120,6 @@ To deploy DocVerifyRAG using Docker, follow these steps:
 ### Usage
 
 Access the web interface and follow the prompts to upload documents, classify them, and verify metadata. The AI-powered anomaly detection system will automatically flag any discrepancies or errors in the document metadata, providing accurate and reliable document management solutions for hospitals.
-
-
 ## Authors
 
 | Name           | Link                                      |
@@ -119,8 +129,7 @@ Access the web interface and follow the prompts to upload documents, classify th
 | Carlos Salgado | [GitHub](https://github.com/salgadev) |
 | Abdul Qadeer | [GitHub](https://github.com/AbdulQadeer-55) |
 
+
 ## License
 
 [![GitLicense](https://img.shields.io/badge/License-MIT-lime.svg)](https://github.com/eliawaefler/DocVerifyRAG/blob/main/LICENSE)
-____
-

backend/generate_metadata.py

@@ -1,4 +1,5 @@
 import os
+import io
 import argparse
 import json
 import openai
@@ -12,13 +13,13 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
 load_dotenv()
 
 
-def ingest(file_path):
-    extension = file_path.split('.')[-1]
-    ext = extension.lower()
-    if ext == 'pdf':
-        loader = UnstructuredPDFLoader(file_path)
-    elif ext == 'txt':
-        loader = TextLoader(file_path)
+import io
+
+def ingest(file_obj, file_ext='pdf'):
+    if file_ext == 'pdf':
+        loader = UnstructuredPDFLoader(file_obj)
+    elif file_ext == 'txt':
+        loader = TextLoader(file_obj)
     else:
         raise NotImplementedError('Only .txt or .pdf files are supported')
 
@@ -29,7 +30,7 @@ def ingest(file_path):
         "\n\n",
         "\n",
         " ",
-        ",",        
+        ",",
         "\uff0c",  # Fullwidth comma
         "\u3001",  # Ideographic comma
         "\uff0e",  # Fullwidth full stop

flake.nix

@@ -14,6 +14,9 @@
     devShells.${system}.default = pkgs.mkShell {
       packages = [
         (pkgs.python311.withPackages (python-pkgs: [
+          python-pkgs.pip # VsCode starts
+          python-pkgs.jupyter
+          python-pkgs.notebook # VsCode ends
           python-pkgs.numpy
           python-pkgs.pandas
           python-pkgs.scipy
@@ -23,15 +26,20 @@
           python-pkgs.langchain
           python-pkgs.langchain-text-splitters
           python-pkgs.unstructured
+          python-pkgs.wrapt # unstructured[local-inference] starts
+          python-pkgs.iso-639
+          python-pkgs.emoji
+          python-pkgs.pillow-heif
+          python-pkgs.magic
+          python-pkgs.poppler-qt5
+          python-pkgs.pytesseract
+          python-pkgs.langdetect # unstructured[local-inference] ends
           python-pkgs.openai
           python-pkgs.pydantic
           python-pkgs.python-dotenv
           python-pkgs.configargparse
           python-pkgs.streamlit
-          python-pkgs.pip
           python-pkgs.lark
-          python-pkgs.jupyter
-          python-pkgs.notebook
           python-pkgs.sentence-transformers
           pkgs.unstructured-api
         ]))

frontend/.vite/deps_temp_eb58ea19/package.json

@@ -0,0 +1,3 @@
+{
+  "type": "module"
+}

frontend/src/components/Features.tsx

@@ -58,7 +58,7 @@ export const Features = () => {
             </CardHeader>
             <CardFooter className="flex flex-wrap md:justify-center gap-4">
               <iframe
-	src="https://sandramsc-docverifyrag.hf.space"
+	src="https://aihackathons-docverifyrag.hf.space"
 	width="850"
 style={{ border: 'none' }}
 	height="750"