update main app file with new github streamlit code

app.py

@@ -1,17 +1,17 @@
 import streamlit as st
-from bs4 import BeautifulSoup
-from langchain.embeddings import HuggingFaceEmbeddings
-import pickle
-import torch
-import io
-from langchain.vectorstores import FAISS
-import json
+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
 
-class CPU_Unpickler(pickle.Unpickler):
-    def find_class(self, module, name):
-        if module == 'torch.storage' and name == '_load_from_bytes':
-            return lambda b: torch.load(io.BytesIO(b), map_location='cpu')
-        else: return super().find_class(module, name)
+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
@@ -20,80 +20,56 @@ def get_hugging_face_model():
   hf = HuggingFaceEmbeddings(model_name=model_name)
   return hf
 
+def get_similar_files(query, db, embeddings):
+  docs_and_scores = db.similarity_search_with_score(query)
+  return docs_and_scores
 
-@st.cache_resource
-def get_db():
-  with open("codesearchdb.pickle", "rb") as f:
-    db = CPU_Unpickler(f).load()
-  print("Loaded db")
-  # save_as_json(db, "codesearchdb.json")  # Save as JSON
-  return db
-
-def save_as_json(data, filename):
-    # Convert the data to a JSON serializable format
-    serializable_data = data_to_serializable(data)
-    with open(filename, "w") as json_file:
-        json.dump(serializable_data, json_file)
-
-def data_to_serializable(data):
-    if isinstance(data, dict):
-        return {k: data_to_serializable(v) for k, v in data.items() if not callable(v) and not isinstance(v, type)}
-    elif isinstance(data, list):
-        return [data_to_serializable(item) for item in data]
-    elif isinstance(data, (str, int, float, bool)) or data is None:
-        return data
-    elif hasattr(data, '__dict__'):
-        return data_to_serializable(data.__dict__)
-    elif hasattr(data, '__slots__'):
-        return {slot: data_to_serializable(getattr(data, slot)) for slot in data.__slots__}
-    else:
-        return str(data)  # Convert any other types to string
-
-def get_similar_links(query, db, embeddings):
-  embedding_vector = embeddings.embed_query(query)
-  docs_and_scores = db.similarity_search_by_vector(embedding_vector, k = 10)
-  hrefs = []
-  for docs in docs_and_scores:
-    html_doc = docs.page_content
-    soup = BeautifulSoup(html_doc, 'html.parser')
-    href = [a['href'] for a in soup.find_all('a', href=True)]
-    hrefs.append(href)
-  links = []
-  for href_list in hrefs:
-      for link in href_list:
-        links.append(link)
-  return links
-
+# STREAMLIT INTERFACE
+st.title("Find Similar Code")
 
-embedding_vector = get_hugging_face_model()
-db = FAISS.load_local("code_sim_index", embedding_vector, allow_dangerous_deserialization=True)
-save_as_json(db, "code_sim_index.json")  # Save as JSON
+USER = st.text_input("Enter the Github User", value = "heaversm")
+REPO = st.text_input("Enter the Github Repository", value = "gdrive-docker")
+FILE_TYPES_TO_LOAD = st.multiselect("Select File Types", [".py", ".ts",".js",".css",".html"], default = [".py"])
 
-st.title("Find Similar Code")
 text_input = st.text_area("Enter a Code Example", value =
 """
-class Solution:
-    def subsets(self, nums: List[int]) -> List[List[int]]:
-        outputs = []
-        def backtrack(k, index, subSet):
-            if index == k:
-                outputs.append(subSet[:])
-                return
-            for i in range(index, len(nums)):
-                backtrack(k, i + 1, subSet + [nums[i]])
-        for j in range(len(nums) + 1):
-            backtrack(j, 0, [])
-        return outputs
+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 Questions")
+
+button = st.button("Find Similar Code")
+
+
 if button:
+  loader = GithubFileLoader(
+    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
-  answer = get_similar_links(query, db, embedding_vector)
-  for link in set(answer):
-      st.write(link)
+  results_with_scores = get_similar_files(query, db, embedding_vector)
+  for doc, score in results_with_scores:
+    print(f"Path: {doc.metadata['path']}, 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 Input Valid Text")
 
-# get_db()
+else:
+  st.info("Please Submit a Code Sample to Find Similar Code")

requirements.txt

@@ -1,8 +1,7 @@
+streamlit
+python-dotenv
 langchain
-sentence-transformers
-bs4
-faiss-cpu
-altair==4.0
 langchain-community
-streamlit
-python-dotenv
+langchain_huggingface
+langchain_text_splitters
+sentence-transformers