Update app.py

app.py

@@ -66,21 +66,44 @@ def process_json():
 
 @app.route('/file_upload',methods=['POST'])
 def file_Upload():
-    
-        #print(request.headers.get('Content-Type'))
-        file=request.files['file']
+        
+        print(request.files.getlist('files[]'))
+        print(request.files)
+        print(request.form)
+        print(request.form.getlist('weburl'))
+        for filename in os.listdir(uploads_dir):
+            file_path = os.path.join(uploads_dir, filename)
+            print("Clearing Doc Directory. Trying to delete"+file_path)
+            try:
+                if os.path.isfile(file_path) or os.path.islink(file_path):
+                    os.unlink(file_path)
+                elif os.path.isdir(file_path):
+                    shutil.rmtree(file_path)
+            except Exception as e:
+                print('Failed to delete %s. Reason: %s' % (file_path, e))
+        
+        documents = []
+        for file in request.files.getlist('files[]'):
+            print(file.filename)
+            file.save(os.path.join(uploads_dir, secure_filename(file.filename)))
+            loader = UnstructuredFileLoader(os.path.join(uploads_dir, secure_filename(file.filename)), mode='elements')
+            documents.extend(loader.load())
+           
+        print(request.form.getlist('weburl'))
+        for url in request.form.getlist('weburl'):
+            print(type(url))
+            urlLoader=WebBaseLoader(url)
+            documents.extend(urlLoader.load())
+        
+        
         print(uploads_dir)
         global chain;
-      
 
-        file.save(os.path.join(uploads_dir, secure_filename(file.filename)))
-        loader = UnstructuredFileLoader(os.path.join(uploads_dir, secure_filename(file.filename)), mode='elements')
-        documents= loader.load()
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
         texts = text_splitter.split_documents(documents)
         embeddings = OpenAIEmbeddings()
-        doc_search = Chroma.from_documents(texts,embeddings)
-        chain = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=doc_search)
+        vectordb = Chroma.from_documents(texts,embeddings)
+        chain = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0.0),chain_type="stuff", retriever=vectordb.as_retriever())
         
         return render_template("index.html")