Update app.py

app.py

@@ -9,27 +9,10 @@ import pickle
 from langchain_community.llms import HuggingFaceEndpoint
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from fastapi import FastAPI, UploadFile, File
-from typing import List
+import gradio as gr
 
-load_dotenv()  # Load environment variables from .env
-
-app = FastAPI()
-
-# Function to extract text from a PDF file
-def extract_text_from_pdf(pdf_path):
-    text = ""
-    doc = fitz.open(pdf_path)
-    for page_num in range(len(doc)):
-        page = doc.load_page(page_num)
-        text += page.get_text()
-    return text
-
-# Function to extract text from a Word document
-def extract_text_from_docx(docx_path):
-    doc = Document(docx_path)
-    text = "\n".join([para.text for para in doc.paragraphs])
-    return text
+# Load environment variables from .env
+load_dotenv()
 
 # Initialize the embedding model
 embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
@@ -38,7 +21,6 @@ embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
 api_token = os.getenv('HUGGINGFACEHUB_API_TOKEN')
 if not api_token:
     raise ValueError("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
-
 print(f"API Token: {api_token[:5]}...")
 
 # Initialize the HuggingFace LLM
@@ -47,7 +29,7 @@ llm = HuggingFaceEndpoint(
     model_kwargs={"api_key": api_token}
 )
 
-# Initialize the HuggingFace embeddings
+# Initialize the HuggingFace embedding
 embedding = HuggingFaceEmbeddings()
 
 # Load or create FAISS index
@@ -61,47 +43,56 @@ else:
     with open(index_path, "wb") as f:
         pickle.dump(index, f)
 
-@app.post("/upload/")
-async def upload_file(files: List[UploadFile] = File(...)):
-    for file in files:
-        content = await file.read()
-        if file.filename.endswith('.pdf'):
-            with open("temp.pdf", "wb") as f:
-                f.write(content)
-            text = extract_text_from_pdf("temp.pdf")
-        elif file.filename.endswith('.docx'):
-            with open("temp.docx", "wb") as f:
-                f.write(content)
-            text = extract_text_from_docx("temp.docx")
-        else:
-            return {"error": "Unsupported file format"}
-
-        # Process the text and update FAISS index
-        sentences = text.split("\n")
-        embeddings = embedding_model.encode(sentences)
-        index.add(np.array(embeddings))
-
-    # Save the updated index
-    with open(index_path, "wb") as f:
-        pickle.dump(index, f)
 
-    return {"message": "Files processed successfully"}
+# Function to extract text from a PDF file
+def extract_text_from_pdf(pdf_path):
+    text = ""
+    doc = fitz.open(pdf_path)
+    for page_num in range(len(doc)):
+        page = doc.load_page(page_num)
+        text += page.get_text()
+    return text
+
+
+# Function to extract text from a Word document
+def extract_text_from_docx(docx_path):
+    doc = Document(docx_path)
+    text = "\n".join([para.text for para in doc.paragraphs])
+    return text
+
+
+def process_and_query(text):
+    # Process the text and update FAISS index (similar to the previous code)
+    sentences = text.split("\n")
+    embeddings = embedding_model.encode(sentences)
+    index.add(np.array(embeddings))
 
-@app.post("/query/")
-async def query(text: str):
-    # Encode the query text
-    query_embedding = embedding_model.encode([text])
-    
     # Search the FAISS index
+    query_embedding = embedding_model.encode([text])
     D, I = index.search(np.array(query_embedding), k=5)
-    
+
     top_documents = []
     for idx in I[0]:
         if idx != -1:  # Ensure that a valid index is found
             top_documents.append(f"Document {idx}")
 
-    return {"top_documents": top_documents}
+    # Generate response using LLM (optional)
+    # You can replace this with your desired LLM interaction logic
+    response = llm.run(inputs=text, max_length=100, temperature=0.7)["generated_text"]
+
+    return {"top_documents": top_documents, "response": response}
+
+
+# Define the Gradio interface
+interface = gr.Interface(
+    fn=process_and_query,
+    inputs="textbox",
+    outputs=["list", "text"],
+    title="Chatbot with Text Processing and Retrieval",
+    description="Upload a document (PDF or Word) or enter text to process. The chatbot will retrieve relevant documents and generate a response (optional).",
+)
+
+# Launch the Gradio interface
+interface.launch()
+
 
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8001)