Create app.py

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+from pydantic import NoneStr
+import os
+from langchain.chains.question_answering import load_qa_chain
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from pypdf import PdfReader
+import mimetypes
+import validators
+import requests
+import tempfile
+import openai
+
+def get_empty_state():
+    return {"knowledge_base": None}
+
+def create_knowledge_base(docs):
+    # split into chunks
+    text_splitter = CharacterTextSplitter(
+        separator="\n", chunk_size=500, chunk_overlap=200, length_function=len
+    )
+    chunks = text_splitter.split_documents(docs)
+    embeddings = OpenAIEmbeddings()
+    knowledge_base = FAISS.from_documents(chunks, embeddings)
+    return knowledge_base
+
+def upload_multiple_urls(urls):
+    all_docs = []
+    file_paths = []
+    for url in urls:
+        if validators.url(url):
+            r = requests.get(url)
+            if r.status_code != 200:
+                raise ValueError(
+                    "Check the url of your file; returned status code %s" % r.status_code
+                )
+            content_type = r.headers.get("content-type")
+            file_extension = mimetypes.guess_extension(content_type)
+            temp_file = tempfile.NamedTemporaryFile(suffix=file_extension, delete=False)
+            temp_file.write(r.content)
+            file_path = temp_file.name
+            loader = UnstructuredFileLoader(file_path, strategy="fast")
+            docs = loader.load()
+            all_docs.extend(docs)
+            file_paths.append(file_path)
+        else:
+            raise ValueError("Please enter a valid URL")
+    knowledge_base = create_knowledge_base(all_docs)
+    return file_paths, {"knowledge_base": knowledge_base}
+
+def answer_question(question, state):
+    try:
+        knowledge_base = state["knowledge_base"]
+        docs = knowledge_base.similarity_search(question)
+
+        llm = OpenAI(temperature=0.4)
+        chain = load_qa_chain(llm, chain_type="stuff")
+        response = chain.run(input_documents=docs, question=question)
+        return response
+    except:
+        return "Please upload Proper Document"
+
+def process_files(urls, question):
+    file_output, state = upload_multiple_urls([url.strip() for url in urls.split(',')])
+    answer = answer_question(question, state)
+    return answer
+
+with gr.Blocks(css="style.css",theme=gr.themes.Soft()) as demo:
+    with gr.Row():
+       gr.HTML("""<img class="leftimage" align="left" src="https://companieslogo.com/img/orig/RAND.AS_BIG-0f1935a4.png?t=1651813778" alt="Image" width="210" height="210">
+                  <img class="rightimage" align="right" src="https://workllama.com/wp-content/uploads/2022/05/WL_Logo.svg" alt="Image" width="210" height="210">""")
+
+    with gr.Row():
+      gr.HTML("""<center><h1>Mulit-URL QA</h1></center>""")
+    with gr.Row():
+      url = gr.Textbox(label="URL")
+    with gr.Row():
+      Question = gr.Textbox(label="Question")
+      with gr.Column(scale=0.30):
+        enter_btn = gr.Button(value="Enter").style(height=100)
+    with gr.Row():
+      Output = gr.Textbox(label="Answer")
+
+    enter_btn.click(process_files,[url,Question],Output)
+demo.title = "URL QA"
+demo.launch()