modify app to output contributors, as well as provide a dropdown list of repos, and ability to list multiple files

app.py

@@ -1,11 +1,14 @@
 import streamlit as st
 import os
 from dotenv import load_dotenv
-from langchain.document_loaders import GithubFileLoader
+# from langchain.document_loaders import GithubFileLoader
+from langchain_community.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
+from github import Github
+from github import Auth
 
 load_dotenv()
 
@@ -13,6 +16,10 @@ load_dotenv()
 GITHUB_ACCESS_TOKEN = os.getenv("GITHUB_ACCESS_TOKEN")
 GITHUB_BASE_URL = "https://github.com/"
 
+# initialize Github
+auth = Auth.Token(GITHUB_ACCESS_TOKEN)
+g = Github(auth=auth)
+
 
 @st.cache_resource
 def get_hugging_face_model():
@@ -24,30 +31,65 @@ def get_similar_files(query, db, embeddings):
   docs_and_scores = db.similarity_search_with_score(query)
   return docs_and_scores
 
+def fetch_repos(username):
+  print(f"Fetching repositories for user: {username}")
+  try:
+    user = g.get_user(username)
+    print(f"User: {user}")
+    return [repo.name for repo in user.get_repos()]
+  except Exception as e:
+    st.error(f"Error fetching repositories: {e}")
+    return []
+
+def get_file_contributors(repo_name, file_path):
+    try:
+        repo = g.get_repo(f"{USER}/{repo_name}")
+        commits = repo.get_commits(path=file_path)
+        contributors = {}
+        for commit in commits:
+            author = commit.author.login if commit.author else "Unknown"
+            if author in contributors:
+                contributors[author] += 1
+            else:
+                contributors[author] = 1
+        return contributors
+    except Exception as e:
+        st.error(f"Error fetching contributors: {e}")
+        return {}
+
+# Initialize session state for repositories
+if "repos" not in st.session_state:
+    st.session_state.repos = []
+
 # STREAMLIT INTERFACE
 st.title("Find Similar Code")
 
 st.markdown("This app takes a code sample you provide, and finds similar code in a Github repository.")
 st.markdown("This functionality could ideally be implemented across multiple repos to allow you to find helpful examples of how to implement the code you are working on writing, or identify other code contributors who could help you resolve your issues")
 
-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"])
+USER = st.text_input("Enter the Github User", value = "Satttoshi")
+
+fetch_repos_button = st.button("Fetch Repositories")
+
+if fetch_repos_button:
+    st.session_state.repos = fetch_repos(USER)
+
+
+REPO = st.selectbox("Select a Github Repository", options=st.session_state.repos)
+
+
+FILE_TYPES_TO_LOAD = st.multiselect("Select File Types", [".py", ".ts",".js",".css",".html"], default = [".ts"])
 
 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")
+find_similar_code_button = st.button("Find Similar Code")
 
-
-if button:
+if find_similar_code_button:
+  print(f"Searching for similar code in {USER}/{REPO}")
   loader = GithubFileLoader(
     repo=f"{USER}/{REPO}",
     access_token=GITHUB_ACCESS_TOKEN,
@@ -63,16 +105,24 @@ if button:
   db = FAISS.from_documents(docs, embedding_vector)
   query = text_input
   results_with_scores = get_similar_files(query, db, embedding_vector)
+  results_with_scores = results_with_scores[:5] #limit to 5 results
   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})")
+    #print all metadata info in the doc.metadata dictionary
+    # for key, value in doc.metadata.items():
+    #     print(f"{key}: {value}")
 
+    path = doc.metadata['path']
+    content = doc.page_content
+    score = round(float(score), 2)
+    contributors = get_file_contributors(REPO, path)
+    print(f"Path: {doc.metadata['path']}, Score: {score}, Contributors: {contributors}")
+    file_link = f"{GITHUB_BASE_URL}{USER}/{REPO}/blob/main/{path}"
+    st.markdown(f"[{path}]({file_link})")
+    for contributor, count in contributors.items():
+        st.write(f"* Contributor: [{contributor}](https://github.com/{contributor}), Commits: {count}")
 
 else:
-  st.info("Please Submit a Code Sample to Find Similar Code")
+  st.info("Please Submit a Code Sample to Find Similar Code")
+
+#https://github.com/heaversm/gdrive-docker/blob/main/gdrive/provider/__init__.py
+#https://github.com/heaversm/gdrive-docker/blob/main/gdrive/provider/__init__.py

requirements.txt

@@ -7,3 +7,4 @@ langchain_text_splitters
 sentence-transformers
 faiss-cpu
 altair==4.0
+PyGithub