.

README.md

@@ -7,7 +7,7 @@ sdk: gradio
 sdk_version: 4.9.1
 app_file: app.py
 pinned: false
----
+--- for local tests, create .gitignore file and load env:
 python3 -m venv venv
 source venv/bin/activate
 pip3 install -r requirements.txt

app.py

@@ -41,7 +41,7 @@ def query_data(query,openai_api_key,mongo_uri):
     # If it's not specified (for example like in the code below),
     # then the default OpenAI model used in LangChain is OpenAI GPT-3.5-turbo, as of August 30, 2023
     
-    llm = OpenAI(openai_api_key=openai_api_key, temperature=0, model_name='gpt-4-1106-preview')
+    llm = OpenAI(openai_api_key=openai_api_key, temperature=0)
 
 
     # Get VectorStoreRetriever: Specifically, Retriever for MongoDB VectorStore.
@@ -51,7 +51,7 @@ def query_data(query,openai_api_key,mongo_uri):
     # Load "stuff" documents chain. Stuff documents chain takes a list of documents,
     # inserts them all into a prompt and passes that prompt to an LLM.
 
-    qa = RetrievalQA.from_chain_type(llm, chain_type="stuff", retriever=retriever, model_name='gpt-4-1106-preview')
+    qa = RetrievalQA.from_chain_type(llm, chain_type="stuff", retriever=retriever)
 
     # Execute the chain
 
@@ -63,19 +63,19 @@ def query_data(query,openai_api_key,mongo_uri):
 
 # Create a web interface for the app, using Gradio
 
-with gr.Blocks(theme=Base(), title="Question Answering App using Vector Search + RAG") as demo:
+with gr.Blocks(theme=Base(), title="MongoDB Atlas Vector Search + RAG Architecture") as demo:
     gr.Markdown(
         """
-        # Question Answering App using Atlas Vector Search + RAG Architecture
+        # MongoDB Atlas Vector Search + RAG Architecture
         """)
-    openai_api_key = gr.Textbox(label = "OpenAI 3.5 API Key", value = "sk-", lines = 1)
-    mongo_uri = gr.Textbox(label = "Mongo URI", value = "mongodb+srv://", lines = 1)
+    openai_api_key = gr.Textbox(label = "OpenAI API Key", value = "sk-", lines = 1)
+    mongo_uri = gr.Textbox(label = "Mongo Atlas URI", value = "mongodb+srv://", lines = 1)
     textbox = gr.Textbox(label="Enter your Question:")
     with gr.Row():
         button = gr.Button("Submit", variant="primary")
     with gr.Column():
-        output1 = gr.Textbox(lines=1, max_lines=10, label="Output with just Atlas Vector Search (returns text field as is):")
-        output2 = gr.Textbox(lines=1, max_lines=10, label="Output generated by chaining Atlas Vector Search to Langchain's RetrieverQA + OpenAI LLM:")
+        output1 = gr.Textbox(lines=1, max_lines=10, label="Atlas Vector Search output (document field as is):")
+        output2 = gr.Textbox(lines=1, max_lines=10, label="Atlas Vector Search output + Langchain's RetrieverQA + OpenAI LLM:")
 
 # Call query_data function upon clicking the Submit button
 

requirements.txt

@@ -1,6 +1,4 @@
 langchain
-langchain-community
-langchain-openai
 pymongo[srv]==4.1.1
 bs4
 openai