Update app.py

changed to load in files from kellogg folder

app.py

@@ -14,6 +14,15 @@ from langchain.prompts import MessagesPlaceholder
 from langchain.agents import AgentExecutor
 from langchain.agents.agent_toolkits import create_retriever_tool
 
+# Function to read files from a folder
+def read_files_from_folder(folder_path):
+    file_data = {}
+    for filename in os.listdir(folder_path):
+        if filename.endswith(".txt"):  # Assuming text files
+            with open(os.path.join(folder_path, filename), 'r') as f:
+                file_data[filename] = f.read()
+    return file_data
+
 print("CHECK - Pinecone vector db setup")
 
 # set up OpenAI environment vars and embeddings
@@ -24,12 +33,21 @@ embeddings = OpenAIEmbeddings()
 index_name = "kellogg-course-assistant"
 
 pinecone.init(
-    api_key=os.getenv("PINECONE_API_KEY"),  # find at app.pinecone.io
-	environment=os.getenv("PINECONE_ENV"),  # next to api key in console
+    api_key=os.getenv("PINECONE_API_KEY"),
+    environment=os.getenv("PINECONE_ENV"),
 )
 
-# load existing index
+# Read files from the "kellogg" folder into a dictionary
+kellogg_data = read_files_from_folder("kellogg")
+
+# Transform the text content to vectors
+kellogg_vectors = {key: embeddings.transform(value) for key, value in kellogg_data.items()}
+
+# Upload the vectors to Pinecone
 vectorsearch = Pinecone.from_existing_index(index_name, embeddings)
+vectorsearch.upsert(items=kellogg_vectors)
+
+# load existing index
 retriever = vectorsearch.as_retriever()
 
 print("CHECK - setting up conversational retrieval agent")