Merge branch 'main' into ingest

.github/workflows/ci-cd.yml

@@ -25,3 +25,4 @@ jobs:
         run: |
           docker build -t ${{ secrets.DOCKER_USERNAME }}/docverifyrag:latest .
           docker push ${{ secrets.DOCKER_USERNAME }}/docverifyrag:latest
+

Dockerfile

@@ -1,27 +1,44 @@
-# Use an official Python runtime as a parent image
-FROM python:3.9-slim
+# Stage 1: Build frontend
+FROM node:latest AS frontend
 
-# Set environment variables
-ENV EXAMPLE 1
-ENV EXAMPLE 2
+# Set working directory for frontend
+WORKDIR /app/frontend
 
-# Set the working directory in the container
-WORKDIR /app
+# Copy frontend source code
+COPY frontend/package.json frontend/package-lock.json ./
+COPY frontend .
 
-# Install system dependencies
-RUN apt-get update \
-	&& apt-get install -y --no-install-recommends gcc \
-	&& rm -rf  /var/lib/apt/lists/*
+# Install dependencies
+RUN npm install
 
-# Install application dependencies
-COPY requirements.txt /app/
+# Build frontend
+RUN npm run build
+
+# Stage 2: Build backend
+FROM python:3.9-slim AS backend
+
+# Set working directory for backend
+WORKDIR /app/backend
+
+# Copy backend source code
+COPY backend .
+
+# Install backend dependencies
+COPY backend/requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy the current directory contents into the container at /app
-COPY . /app/
+# Stage 3: Serve frontend and backend using nginx and gunicorn
+FROM nginx:latest AS production
+
+# Copy built frontend files from the frontend stage to nginx
+COPY --from=frontend /app/frontend/dist /usr/share/nginx/html
+
+# Copy built backend code from the backend stage
+COPY --from=backend /app/backend /app/backend
+
+# Expose port 80 for nginx
+EXPOSE 80
 
-# Expose the port the app runs on
-EXPOSE 5000
+# Start gunicorn server for backend
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]
 
-# Run the application
-CMD ["python", "app.py"]

README.md

@@ -23,13 +23,8 @@
 
 </details>
 
-## Video Demo
-
-[link](https://link.com)
-
-## Web App
-
-[link](https://link.com)
+## TRY the prototype
+[DocVerifyRAG](https://docverify-rag.vercel.app)
 
 ## Screenshots
 
@@ -61,17 +56,35 @@
 
 ### Install locally
 
+#### Step 1 - Frontend
+
 1. Clone the repository:
     ```bash
     $ git clone https://github.com/eliawaefler/DocVerifyRAG.git
     ```
 
-2. Navigate to the project directory:
+2. Navigate to the frontend directory:
     ```bash
-    $ cd DocVerifyRAG
+    $ cd DocVerifyRAG/frontend
     ```
 
 3. Install dependencies:
+    ```bash
+    $ npm install
+    ```
+4. Run project:
+    ```bash
+    $ npm run dev
+    ```
+
+#### Step 2 - Backend
+
+1. Navigate to the backend directory:
+    ```bash
+    $ cd DocVerifyRAG/backend
+    ```
+
+2. Install dependencies:
     ```bash
     $ pip install -r requirements.txt
     ```

requirements.txt → backend/requirements.txt

@@ -2,4 +2,9 @@ langchain_community
 langchain-text-splitters
 langchain-together
 unstructured[local-inference]
-python-dotenv
+python-dotenv
+streamlit
+langchain
+openai
+chromadb
+tiktoken

frontend/package.json

@@ -2,7 +2,7 @@
   "name": "docverifyrag",
   "creadits": "Leo Miranda",
   "private": true,
-  "version": "1.0",
+  "version": "0.1.0",
   "type": "module",
   "scripts": {
     "dev": "vite",

frontend/src/assets/verified-symbol-icon.png:Zone.Identifier

@@ -1,4 +0,0 @@
-[ZoneTransfer]
-ZoneId=3
-ReferrerUrl=https://uxwing.com/wp-content/themes/uxwing/download/arts-graphic-shapes/verified-symbol-icon.png
-HostUrl=https://uxwing.com/wp-content/themes/uxwing/download/arts-graphic-shapes/verified-symbol-icon.png

frontend/src/components/Features.tsx

@@ -5,18 +5,14 @@ import {
   CardFooter,
   CardHeader,
 } from "@/components/ui/card";
-import image4 from "../assets/looking-ahead.png";
-//import { UploadDoc } from "./upload/streamlit_app.py";
 
 interface FeatureProps {
   title: string;
-  image: string;
 }
 
 const features: FeatureProps[] = [
   {
     title: "UPLOAD DOCUMENT",
-    image: image4,
   },
 ];
 
@@ -31,7 +27,7 @@ export const Features = () => {
   return (
     <section
       id="features"
-      className="container py-24 sm:py-32 space-y-8"
+      className="container py-28 sm:py-36 space-y-8"
     >
       <h2 className="text-3xl lg:text-4xl font-bold md:text-center">
         Get Started{" "}
@@ -55,20 +51,18 @@ export const Features = () => {
       </div>
 
       <div className="grid md:grid-cols-2 lg:grid-cols-1">
-        {features.map(({ title, image }: FeatureProps) => (
+        {features.map(({ title }: FeatureProps) => (
           <Card key={title}>
 	   <CardHeader className="text-3xl lg:text-4xl font-bold md:text-center">
               <CardTitle>{title}</CardTitle>
             </CardHeader>
-            <CardFooter>
-              <img
-                src={image}
-                alt="About feature"
-                className="w-[150px] lg:w-[300px] mx-auto"
-              />
-{/* Upload sections */}
-
-     
+            <CardFooter className="flex flex-wrap md:justify-center gap-4">
+              <iframe
+	src="https://sandramsc-docverifyrag.hf.space"
+	style={{ border: 'none' }}
+	width="850"
+	height="450"
+></iframe> 
             </CardFooter>
           </Card>
         ))}

frontend/src/components/Hero.tsx

@@ -1,10 +1,9 @@
-import { HeroCards } from "./HeroCards";
 export const Hero = () => {
   return (
-    <section className="container grid lg:grid-cols-2 place-items-center py-20 md:py-32 gap-10">
+    <section className="container py-30 sm:py-36 space-y-8">
       <div className="text-center lg:text-start space-y-6">
-        <main className="text-5xl md:text-6xl font-bold">
-          <h1 className="inline">
+        <main className="text-8xl lg:text-10xl font-bold">
+          <h1 className="md:text-center">
             <span className="inline bg-gradient-to-r from-[#F596D3]  to-[#D247BF] text-transparent bg-clip-text">
               Doc
             </span>
@@ -13,20 +12,7 @@ export const Hero = () => {
               RAG
             </span></h1>{" "}
         </main>
-
-        <p className="text-xl text-muted-foreground md:w-10/12 mx-auto lg:mx-0">
-          Lorem ipsum dolor sit amet consectetur, adipisicing elit. Veritatis dolor pariatur sit!
-        </p>
-     
       </div>
-
-      {/* Hero cards sections */}
-      <div className="z-10">
-        <HeroCards />
-      </div>
-
-      {/* Shadow effect */}
-      <div className="shadow"></div>
     </section>
   );
 };

frontend/src/components/HowItWorks.tsx

@@ -30,7 +30,7 @@ export const HowItWorks = () => {
   return (
     <section
       id="howItWorks"
-      className="container text-center py-24 sm:py-32"
+      className="container text-center py-22 sm:py-30"
     >
       <h2 className="text-3xl md:text-4xl font-bold ">
         Fast and Accurate{" "}

frontend/src/components/Navbar.tsx

@@ -58,7 +58,7 @@ export const Navbar = () => {
     
               <img
                 src={image}
-                alt="About feature"
+                alt="logo.png"
                 className="w-[18px] lg:w-[28px] mx-2"
               />
         ))}DocVerifyRAG</a>

frontend/src/components/Statistics.tsx

@@ -1,41 +0,0 @@
-export const Statistics = () => {
-  interface statsProps {
-    quantity: string;
-    description: string;
-  }
-
-  const stats: statsProps[] = [
-    {
-      quantity: "2.7K+",
-      description: "Users",
-    },
-    {
-      quantity: "1.8K+",
-      description: "Subscribers",
-    },
-    {
-      quantity: "112",
-      description: "Downloads",
-    },
-    {
-      quantity: "4",
-      description: "Products",
-    },
-  ];
-
-  return (
-    <section id="statistics">
-      <div className="grid grid-cols-2 lg:grid-cols-4 gap-8">
-        {stats.map(({ quantity, description }: statsProps) => (
-          <div
-            key={description}
-            className="space-y-2 text-center"
-          >
-            <h2 className="text-3xl sm:text-4xl font-bold ">{quantity}</h2>
-            <p className="text-xl text-muted-foreground">{description}</p>
-          </div>
-        ))}
-      </div>
-    </section>
-  );
-};

frontend/src/components/upload/.streamlit/config.toml

@@ -1,6 +0,0 @@
-[theme]
-primaryColor="#F63366"
-backgroundColor="#FFFFFF"
-secondaryBackgroundColor="#F0F2F6"
-textColor="#262730"
-font="sans serif"

frontend/src/components/upload/app-v1.py

@@ -1,46 +0,0 @@
-import streamlit as st
-from langchain.llms import OpenAI
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import Chroma
-from langchain.chains import RetrievalQA
-
-def generate_response(uploaded_file, openai_api_key, query_text):
-    # Load document if file is uploaded
-    if uploaded_file is not None:
-        documents = [uploaded_file.read().decode()]
-    # Split documents into chunks
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-    texts = text_splitter.create_documents(documents)
-    # Select embeddings
-    embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
-    # Create a vectorstore from documents
-    db = Chroma.from_documents(texts, embeddings)
-    # Create retriever interface
-    retriever = db.as_retriever()
-    # Create QA chain
-    qa = RetrievalQA.from_chain_type(llm=OpenAI(openai_api_key=openai_api_key), chain_type='stuff', retriever=retriever)
-    return qa.run(query_text)
-
-# Page title
-st.set_page_config(page_title='🦜🔗 Ask the Doc App')
-st.title('🦜🔗 Ask the Doc App')
-
-# File upload
-uploaded_file = st.file_uploader('Upload an article', type='txt')
-# Query text
-query_text = st.text_input('Enter your question:', placeholder = 'Please provide a short summary.', disabled=not uploaded_file)
-
-# Form input and query
-result = []
-with st.form('myform', clear_on_submit=True):
-    openai_api_key = st.text_input('OpenAI API Key', type='password', disabled=not (uploaded_file and query_text))
-    submitted = st.form_submit_button('Submit', disabled=not(uploaded_file and query_text))
-    if submitted and openai_api_key.startswith('sk-'):
-        with st.spinner('Calculating...'):
-            response = generate_response(uploaded_file, openai_api_key, query_text)
-            result.append(response)
-            del openai_api_key
-
-if len(result):
-    st.info(response)

frontend/src/components/upload/streamlit_app.py

@@ -1,47 +0,0 @@
-import streamlit as st
-from langchain.llms import OpenAI
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import Chroma
-from langchain.chains import RetrievalQA
-
-def generate_response(uploaded_file, openai_api_key, query_text):
-    # Load document if file is uploaded
-    if uploaded_file is not None:
-        documents = [uploaded_file.read().decode()]
-        # Split documents into chunks
-        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-        texts = text_splitter.create_documents(documents)
-        # Select embeddings
-        embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
-        # Create a vectorstore from documents
-        db = Chroma.from_documents(texts, embeddings)
-        # Create retriever interface
-        retriever = db.as_retriever()
-        # Create QA chain
-        qa = RetrievalQA.from_chain_type(llm=OpenAI(openai_api_key=openai_api_key), chain_type='stuff', retriever=retriever)
-        return qa.run(query_text)
-
-
-# Page title
-st.set_page_config(page_title='🦜🔗 Ask the Doc App')
-st.title('🦜🔗 Ask the Doc App')
-
-# File upload
-uploaded_file = st.file_uploader('Upload an article', type='txt')
-# Query text
-query_text = st.text_input('Enter your question:', placeholder = 'Please provide a short summary.', disabled=not uploaded_file)
-
-# Form input and query
-result = []
-with st.form('myform', clear_on_submit=True):
-    openai_api_key = st.text_input('OpenAI API Key', type='password', disabled=not (uploaded_file and query_text))
-    submitted = st.form_submit_button('Submit', disabled=not(uploaded_file and query_text))
-    if submitted and openai_api_key.startswith('sk-'):
-        with st.spinner('Calculating...'):
-            response = generate_response(uploaded_file, openai_api_key, query_text)
-            result.append(response)
-            del openai_api_key
-
-if len(result):
-    st.info(response)