linted used black and ruff

Author: codinglabsong

setup.py

@@ -21,4 +21,4 @@
         # "torchmetrics[image]",
         # "boto3",
     ],
-)
+)

src/any_chatbot/agent.py

@@ -1,5 +1,6 @@
 import getpass
 import os
+import random
 from dotenv import load_dotenv
 from pathlib import Path
 
@@ -41,7 +42,6 @@
 
 # PROMPT
 # specify an ID for the thread
-import random
 # config = {"configurable": {"thread_id": "abc123"}}
 config = {"configurable": {"thread_id": random.random()}}
 
@@ -57,4 +57,3 @@
     config=config,
 ):
     event["messages"][-1].pretty_print()
-

src/any_chatbot/indexing.py

@@ -11,6 +11,7 @@
 BASE = Path(__file__).parent.parent.parent
 DATA = BASE / "data"
 
+
 def index_text_docs(
     data_pth: Path = DATA,
 ):
@@ -32,27 +33,24 @@ def index_text_docs(
             "**/*.jpeg",
             "**/*.tiff",
         ],
-        loader_cls=UnstructuredFileLoader
+        loader_cls=UnstructuredFileLoader,
     )
     print(f"Loading files from {data_pth}")
     docs = loader.load()
     print(f"Loaded {len(docs)} files")
 
     # Split the texts
     text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=1000, 
-        chunk_overlap=200, 
+        chunk_size=1000,
+        chunk_overlap=200,
         add_start_index=True,
-        separators=["\n\n", "\n", " ", ""],  
+        separators=["\n\n", "\n", " ", ""],
     )
     all_splits = text_splitter.split_documents(docs)
     print(len(all_splits))
 
     # index the docs
     ids = vector_store.add_documents(documents=all_splits)
     print(len(ids))
-    
-    return embeddings, vector_store
-
-
 
+    return embeddings, vector_store

src/any_chatbot/tools.py

@@ -1,16 +1,15 @@
 from typing import Tuple, List
 from langchain_core.tools import tool
 from langchain.vectorstores.base import VectorStore
-from langchain.schema import Document    
+from langchain.schema import Document
+
 
 def initialize_retrieve_tool(vector_store: VectorStore):
     @tool(
         description="Retrieve information related to a query",
         response_format="content_and_artifact",
     )
-    def retrieve(
-        query: str
-    ) -> Tuple[str, List[Document]]:
+    def retrieve(query: str) -> Tuple[str, List[Document]]:
         retrieved_docs = vector_store.similarity_search(query, k=3)
         serialized = "\n\n".join(
             (f"Source: {doc.metadata}\nContent: {doc.page_content}")