app.py

import gradio as gr
from langchain import LlamaCpp
from langchain.callbacks import StreamingStdOutCallbackHandler
from langchain.callbacks.manager import CallbackManager
from langchain.chains.question_answering import load_qa_chain
import dill
def greet(name):
    db = dill.load(open("client_embebedings.mate", "rb"))
    docs = db.similarity_search(name)
    return chain.run(input_documents=docs, question=name)

def greet1(name):
    return "Hello ya client" +name

iface = gr.Blocks()

with iface:
    callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
    chain = load_qa_chain( LlamaCpp(
        model_path="llama-13B-Q4_K_M.gguf",
        temperature=0,
        top_p= 1,
        callback_manager=callback_manager,
        verbose=True,

    ), chain_type="stuff")
    name = gr.Textbox(label="Name")
    output = gr.Textbox(label="Output Box")

    greet_btn = gr.Button("Greet")
    greet_btn.click(fn=greet, inputs=name, outputs=output, api_name="greet")

    greet1_btn = gr.Button("Greet1")
    greet1_btn.click(fn=greet1, inputs=name, outputs=output, api_name="testing")

iface.launch()