app.py

# -*- coding: utf-8 -*-
"""code-search.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1-TlihNx5XCiVSxUHDF1oHFNcfpuy_k0N
"""

# Install Cohere for embeddings

import cohere
import numpy as np
import pandas as pd
import gradio as gr

from sklearn.metrics.pairwise import cosine_similarity
from annoy import AnnoyIndex
import warnings
warnings.filterwarnings('ignore')
pd.set_option('display.max_colwidth', None)

data_df = pd.read_csv('functions_data.csv')
#data_df.head()

data_df['docstring'].fillna('not specified', inplace=True)

# Paste your API key here. Remember to not share publicly
api_key = '2IdvZuDAwqcpMuwN3yjAXBOHKAT1Mqxr4N8hZFKN'

# Create and retrieve a Cohere API key from dashboard.cohere.ai/welcome/register
co = cohere.Client(api_key)


search_index = AnnoyIndex(4096, 'angular')
search_index.load('code.ann') # super fast, will just mmap the file

def get_code(query):
    # Get the query's embedding
    query_embed = co.embed(texts=[query],
                    model="large",
                    truncate="LEFT").embeddings

    # Retrieve the nearest neighbors
    similar_item_ids = search_index.get_nns_by_vector(query_embed[0],3,
                                                    include_distances=True)
    
    return data_df.iloc[similar_item_ids[0]]['function_body'] , data_df.iloc[similar_item_ids[0]]['file_path']

iface = gr.Interface(fn=get_code, inputs="text", outputs=[gr.Markdown(), "text"])
iface.launch()