integrating OPENAI and Langchain into the ChatUI, comments added for explainations with source links

Signed-off-by: BergZain <50025962+bergzain@users.noreply.github.com>

Author: bergzain

src/ChatUI_streamlit/LLMModel.py

@@ -9,21 +9,22 @@
 from langchain.prompts import PromptTemplate
 
 
-YourAPIKey = os.environ['OPENAI_API_KEY']
+YourAPIKey = os.environ['OPENAI_API_KEY'] # This is the API key for OpenAI
 
-load_dotenv()
+load_dotenv() # Load the .env file
 
-openai_api_key=os.getenv('OPENAI_API_KEY', 'YourAPIKey')
+openai_api_key=os.getenv('OPENAI_API_KEY', 'YourAPIKey') # Get the API key from the .env file
 
-llm = ChatOpenAI(model_name='gpt-3.5-turbo', openai_api_key=openai_api_key)
+llm = ChatOpenAI(model_name='gpt-3.5-turbo', openai_api_key=openai_api_key) # Load the LLM model
 
 
-embeddings = OpenAIEmbeddings(disallowed_special=(), openai_api_key=openai_api_key)
+embeddings = OpenAIEmbeddings(disallowed_special=(), openai_api_key=openai_api_key) # Load the embeddings
 
+# This is the root directory for the documents i want to create the RAG from
 root_dir = '/Users/zainhazzouri/projects/RAG-Playground/core/src/sdk/python/rtdip_sdk/pipelines'
 docs = []
 
-# Go through each folder
+# Go through each folder to extract all the files
 for dirpath, dirnames, filenames in os.walk(root_dir):
 
     # Go through each file
@@ -35,7 +36,9 @@
         except Exception as e:
             pass
 
-docsearch = FAISS.from_documents(docs, embeddings)
+docsearch = FAISS.from_documents(docs, embeddings) # Create the FAISS index
+# source https://python.langchain.com/docs/integrations/vectorstores/faiss_async
 
-# Get our retriever ready
+# Get our retriever ready for the RAG or creating the chain
 RAG = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=docsearch.as_retriever())
+# source link for reference https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA