Update app.py
Browse files
app.py
CHANGED
@@ -78,7 +78,7 @@ def generate(query, api_key):
|
|
78 |
with gr.Blocks() as demo:
|
79 |
gr.Markdown(
|
80 |
"""
|
81 |
-
# Retrieval Augmented Generation with GPT 3.5 Turbo
|
82 |
### This demo uses the GPT 3.5 Turbo LLM and MongoDB Atlas Vector Search for fast and performant Retrieval Augmented Generation (RAG).
|
83 |
### The context is the new Oppenheimer movie's entire wikipedia page. The movie came out very recently in July, 2023, so the GPT 3.5 turbo model is not aware of it.
|
84 |
Retrieval Augmented Generation (RAG) enables us to retrieve just the few small chunks of the document that are relevant to the our query and inject it into our prompt.
|
|
|
78 |
with gr.Blocks() as demo:
|
79 |
gr.Markdown(
|
80 |
"""
|
81 |
+
# Retrieval Augmented Generation with GPT 3.5 Turbo, MongoDB Atlas Vector Search, and LlamaIndex: Question Answering demo
|
82 |
### This demo uses the GPT 3.5 Turbo LLM and MongoDB Atlas Vector Search for fast and performant Retrieval Augmented Generation (RAG).
|
83 |
### The context is the new Oppenheimer movie's entire wikipedia page. The movie came out very recently in July, 2023, so the GPT 3.5 turbo model is not aware of it.
|
84 |
Retrieval Augmented Generation (RAG) enables us to retrieve just the few small chunks of the document that are relevant to the our query and inject it into our prompt.
|