update

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.psd filter=lfs diff=lfs merge=lfs -text
 *.csv filter=lfs diff=lfs merge=lfs -text
+*.cache filter=lfs diff=lfs merge=lfs -text

app.py

@@ -4,6 +4,8 @@ from google.colab import userdata
 from langchain import OpenAI, LLMMathChain, SerpAPIWrapper
 from langchain.agents import initialize_agent, Tool, AgentExecutor
 from langchain_community.chat_models import ChatOpenAI
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.storage import LocalFileStore
 import os
 import chainlit as cl
 import openai
@@ -28,6 +30,20 @@ from dotenv import dotenv_values
 # get keys
 my_secrets = dotenv_values("key.env")
 
+# download data
+#dataset = load_dataset("ShubhamChoksi/IMDB_Movies")
+#split_name = "train" # Change this to the split you want to save
+#data = dataset[split_name]
+
+# Convert the dataset to a pandas DataFrame
+#df = pd.DataFrame(data)
+
+# Define the path where you want to save the CSV file
+#csv_file_path =  'data.csv'
+
+# Save the DataFrame to a CSV file
+#df.to_csv(csv_file_path, index=False)
+
 #load the csv
 loader = TextLoader('data.csv')
 documents = loader.load()
@@ -44,7 +60,13 @@ docs = text_splitter.split_documents(documents)
 
 # create embeddings
 underlying_embeddings = OpenAIEmbeddings(model="text-embedding-ada-002",api_key=my_secrets["OPEN_API_KEY"])
-db = FAISS.from_documents(docs, underlying_embeddings)
+store = LocalFileStore("./cache/")
+
+cached_embedder = CacheBackedEmbeddings.from_bytes_store(
+    underlying_embeddings, store, namespace=underlying_embeddings.model
+)
+
+db = FAISS.from_documents(docs, cached_embedder)
 
 # Get the retriever for the Chat Model
 retriever = db.as_retriever(

cache/text-embedding-ada-00217774108-46e7-520b-ae73-abbed038011a.cache

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d362eb5113dd5397957c9e6a74ee8cf013f06796a13c6cc5d7dbea5c1155845
+size 34480

chainlit.md

@@ -0,0 +1 @@
+# Welcome to Andy's Movie RAG for all your Movie Questions! 🚀🤖