github.py

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")
USER = "heaversm"
REPO = "gdrive-docker"
GITHUB_BASE_URL = "https://github.com/"


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

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

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(
        (".py", ".ts")
    ),  # load all python and typescript files
)
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)
model_name = "mchochlov/codebert-base-cd-ft"

query = """
def create_app():
    app = connexion.FlaskApp(__name__, specification_dir="../.openapi")
    app.add_api(
        API_VERSION, resolver=connexion.resolver.RelativeResolver("provider.app")
    )
"""
results_with_scores = get_similar_files(query, db, embedding_vector)
print ("retrieved!!!")
print(f"Number of results: {len(results_with_scores)}")

# score is a distance score, the lower the better
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}"

print(f"Top file link: {top_file_link}")