Update app.py

app.py

@@ -1,63 +1,39 @@
+import os
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain import vectorstores
+from langchain import chains
+from langchain import llms
+from langchain.embeddings import HuggingFaceEmbeddings
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+llm = llms.AI21(ai21_api_key='diNNQzvL40ZnBnEQkIBwNESWjtj792NG')
+
+def pdf_qa(pdf, query):
+    if pdf is not None:
+        pdf_reader = PdfReader(pdf)
+        texts = ""
+        for page in pdf_reader.pages:
+            texts += page.extract_text()
+        text_splitter = CharacterTextSplitter(
+            separator="\n",
+            chunk_size=1000,
+            chunk_overlap=0
+        )
+        chunks = text_splitter.split_text(texts)
+        embeddings = HuggingFaceEmbeddings()
+        db = vectorstores.Chroma.from_texts(chunks, embeddings)
+        retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 10})
+        qa = chains.ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever)
+        chat_history = []
+        if query:
+            result = qa({"question": query, "chat_history": chat_history})
+            return result["answer"]
+    return "Please upload a PDF and enter a query."
+
+pdf_input = gr.inputs.File(label="Upload your PDF", type="file", file_count="single")
+query_input = gr.inputs.Textbox(label="Ask a question in PDF")
+output = gr.outputs.Textbox(label="Answer")
+
+gr.Interface(fn=pdf_qa, inputs=[pdf_input, query_input], outputs=output, title="PDF QA").launch()