File size: 1,412 Bytes
157cf8c 8e61694 82f04bb 8e61694 157cf8c 0230ec8 157cf8c 68e1a2a 157cf8c 68e1a2a 157cf8c 0230ec8 157cf8c 0230ec8 157cf8c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import openai
import faiss
import numpy as np
import os
import gradio as gr
openai.api_key = os.environ['api_top']
text_file_path = 'risale.txt'
# read the text file
with open(text_file_path, 'r', encoding='utf-8') as file:
text_content = file.read()
# split text into sentences
allText = [sentence.strip() for sentence in text_content.split('<br>') if sentence.strip()]
def encode_open(input):
# you can change model if you want different
MODEL = "text-embedding-ada-002"
res = openai.Embedding.create(
input=input, engine=MODEL
)
embeds = [record['embedding'] for record in res['data']]
import torch
embeds=torch.FloatTensor(embeds)
return embeds
encoded_data=encode_open(allText)
d=encoded_data.shape[1]
index = faiss.IndexIDMap(faiss.IndexFlatIP(d))
index.add_with_ids(encoded_data, np.arange(encoded_data.shape[0]))
def search_openai_pdf(query, k=10):
try:
query_vector = encode_open([query])
top_k = index.search(query_vector, k)
return [
allText[_id] for _id in top_k[1][0]
]
except Exception as e:
return ["Hata oluştu", e]
iface = gr.Interface(
fn=search_openai_pdf,
inputs=gr.Textbox(placeholder="Fihristte aramak için bir şeyler yaz.",label='query'),
outputs=gr.Textbox(label="Sonuçlar"),
live=False,
title="Sözler Fihristi Anlamsal Arama Motoru"
)
iface.launch()
|