Create app.py

app.py

@@ -0,0 +1,45 @@
+import os
+from PyPDF2 import PdfReader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains.question_answering import load_qa_chain
+import gradio as gr
+
+
+
+
+def submitYourDocument(doc):
+  reader = PdfReader(doc)
+  # read data from the file and put them into a variable called raw_text
+  raw_text = ''
+  for i, page in enumerate(reader.pages):
+    text = page.extract_text()
+    if text:
+        raw_text += text
+  text_splitter = CharacterTextSplitter(        
+    separator = "\n",
+    chunk_size = 1000,
+    chunk_overlap  = 200,
+    length_function = len,
+  )
+  texts = text_splitter.split_text(raw_text)
+  return texts
+
+    
+def main(doc,prompt):
+  result=submitYourDocument(doc)
+  embeddings = HuggingFaceEmbeddings()
+  db = FAISS.from_texts(result, embeddings)
+  llm=HuggingFaceHub(repo_id="google/flan-t5-xxl",model_kwargs={"temperature":1, "max_length":512})
+  chain=load_qa_chain(llm,chain_type="stuff")
+  query =prompt
+  docs = db.similarity_search(query)
+  return chain.run(input_documents=docs, question=query)
+
+interface=gr.Interface(fn=main,inputs=[gr.File(label="Upload file"),gr.components.Textbox(label="Type Question Related to Uploaded Document")],
+                       outputs=gr.components.Textbox("Answer.."))
+interface.launch(debug=True)
+
+