github_st.py

import streamlit as st
import os
from dotenv import load_dotenv
from langchain.document_loaders import GithubFileLoader
# from langchain.embeddings import HuggingFaceEmbeddings
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_text_splitters import CharacterTextSplitter

load_dotenv()

#get the GITHUB_ACCESS_TOKEN from the .env file
GITHUB_ACCESS_TOKEN = os.getenv("GITHUB_ACCESS_TOKEN")
GITHUB_BASE_URL = "https://github.com/"


@st.cache_resource
def get_hugging_face_model():
  model_name = "mchochlov/codebert-base-cd-ft"
  hf = HuggingFaceEmbeddings(model_name=model_name)
  return hf

def get_similar_files(query, db, embeddings):
  # embedding_vector = embeddings.embed_query(query)
  # docs_and_scores = db.similarity_search_by_vector(embedding_vector, k = 10)
  docs_and_scores = db.similarity_search_with_score(query)
  return docs_and_scores




st.title("Find Similar Code")

#streamlit text input for USER
USER = st.text_input("Enter the Github User", value = "heaversm")
#streamlit text input for REPO
REPO = st.text_input("Enter the Github Repository", value = "gdrive-docker")

#streamlit file type selector
FILE_TYPES_TO_LOAD = st.multiselect("Select File Types", [".py", ".ts",".js",".css",".html"], default = [".py"])


text_input = st.text_area("Enter a Code Example", value =
"""
def create_app():
    app = connexion.FlaskApp(__name__, specification_dir="../.openapi")
    app.add_api(
        API_VERSION, resolver=connexion.resolver.RelativeResolver("provider.app")
    )
""", height = 330
)

button = st.button("Find Similar Code")


if button:
  loader = GithubFileLoader(
    #repo is USER/REPO
    repo=f"{USER}/{REPO}",
    access_token=GITHUB_ACCESS_TOKEN,
    github_api_url="https://api.github.com",
    file_filter=lambda file_path: file_path.endswith(
      tuple(FILE_TYPES_TO_LOAD)
    )
  )
  documents = loader.load()
  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
  docs = text_splitter.split_documents(documents)
  embedding_vector = get_hugging_face_model()
  db = FAISS.from_documents(docs, embedding_vector)
  query = text_input
  results_with_scores = get_similar_files(query, db, embedding_vector)
  for doc, score in results_with_scores:
    print(f"Metadata: {doc.metadata}, Score: {score}")

  top_file_path = results_with_scores[0][0].metadata['path']
  top_file_content = results_with_scores[0][0].page_content
  top_file_score = results_with_scores[0][1]
  top_file_link = f"{GITHUB_BASE_URL}{USER}/{REPO}/blob/main/{top_file_path}"
  # write a clickable link in streamlit
  st.markdown(f"[Top file link]({top_file_link})")


else:
  st.info("Please Submit a Code Sample")