add initial ui

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+
+from langchain.document_loaders import OnlinePDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.llms import HuggingFaceHub
+from langchain.embeddings import HuggingFaceHubEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQA
+import os
+
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = ""
+
+
+def file_upload_click(pdf_doc):  
+    loader = OnlinePDFLoader(pdf_doc.name)
+    documents = loader.load()
+    text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=0)
+    texts = text_splitter.split_documents(documents)
+    embeddings = HuggingFaceHubEmbeddings()
+    db = Chroma.from_documents(texts, embeddings)
+    retriever = db.as_retriever()
+    llm = HuggingFaceHub(repo_id="OpenAssistant/oasst-sft-1-pythia-12b", model_kwargs={"temperature":0.1, "max_new_tokens":250})
+    global qa 
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
+    return "Ready"
+
+def add_text(history, text):
+    history = history + [(text, None)]
+    return history, ""
+
+def bot(history):
+    query=history[-1][0]
+    response = qa({"query": query})
+    history[-1][1] = response['result']
+    print(history)
+    return history
+
+
+with gr.Blocks() as demo:
+    status_label = gr.Label(value='Start')
+    file_upload = gr.File(label="Uplaod pdf", file_types=['.pdf'], type="file")
+    file_upload_button= gr.Button('upload file')
+    chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
+    question = gr.Textbox(label="Question", placeholder="Type your question and click submit")
+    submit_btn = gr.Button("Send message")
+    file_upload_button.click(file_upload_click, inputs=[file_upload], outputs=[status_label], queue=False)
+    submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
+        bot, chatbot, chatbot
+    )
+
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,5 @@
+huggingface_hub
+chromadb
+langchain
+unstructured
+gradio