Clean up files

.gitignore

@@ -0,0 +1,5 @@
+constants.py
+__pycache__
+persist/
+.DS_Store
+.chroma/

README.md

@@ -8,14 +8,21 @@ Here's the [YouTube Video](https://youtu.be/9AXP7tCI9PI).
 
 Install [Langchain](https://github.com/hwchase17/langchain) and other required packages.
 ```
-pip install langchain openai chromadb tiktoken beautifulsoup4
+pip install langchain openai chromadb tiktoken unstructured
 ```
 Modify `constants.py` to use your own [OpenAI API key](https://platform.openai.com/account/api-keys).
 
-Place your own data into `data.txt`.
+Place your own data into `data/data.txt`.
 
 ## Example usage
+Test reading `data/data.txt` file.
 ```
 > python chatgpt.py "what is my dog's name"
 Your dog's name is Sunny.
 ```
+
+Test reading `data/cat.pdf` file.
+```
+> python chatgpt.py "what is my cat's name"
+Your cat's name is Muffy.
+```

chatgpt.py

@@ -7,27 +7,25 @@
 from langchain.document_loaders import DirectoryLoader, TextLoader
 from langchain.embeddings import OpenAIEmbeddings
 from langchain.indexes import VectorstoreIndexCreator
+from langchain.indexes.vectorstore import VectorStoreIndexWrapper
 from langchain.llms import OpenAI
 from langchain.vectorstores import Chroma
 
 import constants
 
 os.environ["OPENAI_API_KEY"] = constants.APIKEY
 
-# Enable to cache & reuse the model to disk (for repeated queries on the same data)
+# Enable to save to disk & reuse the model (for repeated queries on the same data)
 PERSIST = False
 
 query = sys.argv[1]
 
 if PERSIST and os.path.exists("persist"):
   print("Reusing index...\n")
   vectorstore = Chroma(persist_directory="persist", embedding_function=OpenAIEmbeddings())
-  from langchain.indexes.vectorstore import VectorStoreIndexWrapper
   index = VectorStoreIndexWrapper(vectorstore=vectorstore)
 else:
-  loader = TextLoader('data.txt')
-  # This code can also import folders, including various filetypes like PDFs using the DirectoryLoader.
-  # loader = DirectoryLoader(".", glob="*.txt")
+  loader = DirectoryLoader("data/")
   if PERSIST:
     index = VectorstoreIndexCreator(vectorstore_kwargs={"persist_directory":"persist"}).from_loaders([loader])
   else:

constants.py

@@ -1 +1 @@
-APIKEY = "<your OpenAI API Key>"
+APIKEY = "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"