app.py

import gradio as gr
import openai
import pandas as pd 
import numpy as np
import csv
from datasets import load_dataset
openai.api_key="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"
from openai.embeddings_utils import get_embedding
from openai.embeddings_utils import cosine_similarity

Bio_embeddings = load_dataset('vjain/biology_AP_embeddings')
df =pd.read_parquet("AP_bio_embeddings.parquet")
#df = pd.read_csv("TA_embeddings.csv")
#df["embedding"]=df["embedding"].apply(eval).apply(np.array)
def reply(input):
    
    input = input
    input_vector = get_embedding(input, engine="text-embedding-ada-002")
    df["similiarities"]=df["embedding"].apply(lambda x: cosine_similarity(x,input_vector))
    data = df.sort_values("similiarities", ascending=False).head(20)
    data.to_csv("sorted.csv")
    context = []
    for i, row in data.iterrows():
        context.append(row['text'])
    context
    text = "\n".join(context)
    context = text
    prompt = f"""
                Answer the following question If you don't know the answer for certain, say I don't know.
                Context: {context}

                Q: {input}

                """      
    return openai.Completion.create(
                    prompt=prompt,
                    temperature=1,
                    max_tokens=500,
                    top_p=1,
                    frequency_penalty=0,
                    presence_penalty=0,
                    model="text-davinci-003"
                )["choices"][0]["text"].strip(" \n")
    

input_text = gr.inputs.Textbox(label="Enter your Trading questions here")
text_output = gr.outputs.Textbox(label="Answer")

ui = gr.Interface(fn=reply,
                  inputs=input_text,
                  outputs=[text_output],
                  theme="compact",
                  layout="vertical",
                  inputs_layout="stacked",
                  outputs_layout="stacked",
                  allow_flagging=False)



ui.launch()