Upload 7 files

.env

@@ -0,0 +1 @@
+GROQ_API_KEY="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"

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.py linguist-language=Python
+*.txt linguist-language=Text

app.py

@@ -0,0 +1,32 @@
+import streamlit as st
+import pandas as pd
+import os
+from utils import process_uploaded_file
+from groq_api import ask_groq
+
+st.set_page_config(page_title="Multidoc Chat", layout="wide")
+
+st.title("📄 Multidoc Chat - Ask Anything About Your Files")
+
+uploaded_file = st.file_uploader("Upload PDF or Excel", type=["pdf", "xlsx"])
+
+if uploaded_file:
+    with st.spinner("Processing file..."):
+        extracted_text = process_uploaded_file(uploaded_file)
+
+    if "history" not in st.session_state:
+        st.session_state.history = []
+
+    st.text_area("Extracted Text Preview", extracted_text[:1000], height=150, disabled=True)
+
+    user_query = st.text_input("Ask something about the document:")
+
+    if st.button("Get Answer") and user_query:
+        response = ask_groq(user_query, extracted_text)
+        st.session_state.history.append((user_query, response))
+    
+    if st.session_state.history:
+        st.write("### Chat History:")
+        for q, a in st.session_state.history:
+            st.write(f"**Q:** {q}")
+            st.write(f"**A:** {a}")

groq_api.py

@@ -0,0 +1,24 @@
+import os
+import requests
+from dotenv import load_dotenv
+
+load_dotenv()
+
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+MODEL_NAME = "llama3-8b-chat"  # Update model as needed
+API_URL = "https://api.groq.com/v1/chat/completions"
+
+def ask_groq(user_query, context_text):
+    """Send user query and extracted text to Groq API"""
+    headers = {"Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json"}
+    
+    payload = {
+        "model": MODEL_NAME,
+        "messages": [
+            {"role": "system", "content": "You are an AI that answers questions based on the given document."},
+            {"role": "user", "content": f"Document: {context_text[:4000]}\n\nQuestion: {user_query}"}
+        ]
+    }
+    
+    response = requests.post(API_URL, json=payload, headers=headers)
+    return response.json().get("choices", [{}])[0].get("message", {}).get("content", "No response")

readme.md

@@ -0,0 +1,17 @@
+# 📄 Multidoc Chat - Hugging Face Space
+
+Multidoc Chat allows users to upload **PDFs and Excel files** and ask questions about the content. It uses:
+- **Groq API** + **Llama model** for answering queries
+- **Streamlit** for a simple and interactive UI
+
+## 🚀 Features
+- Upload **PDFs & Excel** files
+- Extract text automatically
+- Ask questions & get AI-powered responses
+- Interactive chat history
+
+## 🔧 Installation
+1. **Clone this repository:**
+   ```sh
+   git clone https://huggingface.co/spaces/akashshahade/multidoc_chat
+   cd multidoc_chat

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+groq
+pypdf
+pandas
+openpyxl
+python-dotenv

utils.py

@@ -0,0 +1,26 @@
+import pandas as pd
+import io
+from pypdf import PdfReader
+
+def process_uploaded_file(uploaded_file):
+    """Extracts text from uploaded PDF or Excel files"""
+    if uploaded_file.type == "application/pdf":
+        return extract_text_from_pdf(uploaded_file)
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet":
+        return extract_text_from_excel(uploaded_file)
+    else:
+        return "Unsupported file format."
+
+def extract_text_from_pdf(pdf_file):
+    """Extract text from a PDF"""
+    reader = PdfReader(pdf_file)
+    text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])
+    return text
+
+def extract_text_from_excel(excel_file):
+    """Extract text from an Excel file"""
+    df = pd.read_excel(excel_file, sheet_name=None)
+    text = ""
+    for sheet, data in df.items():
+        text += f"\nSheet: {sheet}\n" + data.to_string(index=False)
+    return text