Duplicate from Noobian/PDF-QA

Co-authored-by: Abdullah Saleh <Noobian@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,14 @@
+---
+title: PDF QA
+emoji: 🐠
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 3.19.1
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: Noobian/PDF-QA
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import PyPDF2
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores.faiss import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain import OpenAI, VectorDBQA
+
+import os
+openai_api_key = os.environ["OPENAI_API_KEY"] 
+
+
+def pdf_to_text(pdf_file, query):
+  # Open the PDF file in binary mode
+  with open(pdf_file.name, 'rb') as pdf_file:
+      # Create a PDF reader object
+      pdf_reader = PyPDF2.PdfReader(pdf_file)
+
+      # Create an empty string to store the text
+      text = ""
+
+      # Loop through each page of the PDF
+      for page_num in range(len(pdf_reader.pages)):
+          # Get the page object
+          page = pdf_reader.pages[page_num]
+          # Extract the texst from the page and add it to the text variable
+          text += page.extract_text()
+    #embedding step 
+  text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+  texts = text_splitter.split_text(text)
+
+  embeddings = OpenAIEmbeddings()
+  #vector store
+  vectorstore = FAISS.from_texts(texts, embeddings)
+
+    #inference
+  qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=vectorstore)
+  return qa.run(query)
+
+
+      
+
+
+# Define the Gradio interface
+pdf_input = gr.inputs.File(label="PDF File")
+query_input = gr.inputs.Textbox(label="Query")
+outputs = gr.outputs.Textbox(label="Chatbot Response")
+interface = gr.Interface(fn=pdf_to_text, inputs=[pdf_input, query_input], outputs=outputs)
+
+# Run the interface
+interface.launch(debug = True)

requirements.txt

@@ -0,0 +1,5 @@
+openai
+langchain 
+faiss-cpu 
+gradio 
+PyPDF2