Update app.py

app.py

@@ -33,9 +33,7 @@ CHROMA_DIR  = "/data/chroma"
 YOUTUBE_DIR = "/data/youtube"
 
 PDF_URL       = "https://arxiv.org/pdf/2303.08774.pdf"
-WEB_URL_1     = "https://openai.com/research/gpt-4"
-WEB_URL_2     = "https://platform.openai.com/docs/introduction"
-WEB_URL_3     = "https://platform.openai.com/docs/api-reference"
+WEB_URL       = "https://openai.com/research/gpt-4"
 YOUTUBE_URL_1 = "https://www.youtube.com/watch?v=--khbXchTeE"
 YOUTUBE_URL_2 = "https://www.youtube.com/watch?v=hdhZwyf24mE"
 YOUTUBE_URL_3 = "https://www.youtube.com/watch?v=vw-KWfKwvTQ"
@@ -55,10 +53,6 @@ def invoke(openai_api_key, use_rag, prompt):
         # Load Web
         #loader = WebBaseLoader(WEB_URL_1)
         #docs.extend(loader.load())
-        #loader = WebBaseLoader(WEB_URL_2)
-        #docs.extend(loader.load())
-        #loader = WebBaseLoader(WEB_URL_3)
-        #docs.extend(loader.load())
         # Load YouTube
         #loader = GenericLoader(YoutubeAudioLoader([YOUTUBE_URL_1,
         #                                           YOUTUBE_URL_2,
@@ -90,16 +84,16 @@ def invoke(openai_api_key, use_rag, prompt):
 description = """<strong>Overview:</strong> The app demonstrates how to use a <strong>Large Language Model (LLM)</strong> with <strong>Retrieval Augmented Generation (RAG)</strong> 
                  on <strong>external data</strong> (private/public & structured/unstructured).\n\n
                  <strong>Instructions:</strong> Enter an OpenAI API key and perform LLM use cases (semantic search, summarization, translation, etc.) on 
-                 <a href='""" + YOUTUBE_URL_1 + """'>YouTube</a>, <a href='""" + PDF_URL + """'>PDF</a>, and <a href='""" + WEB_URL_1 + """'>Web</a> 
+                 <a href='""" + YOUTUBE_URL_1 + """'>YouTube</a>, <a href='""" + PDF_URL + """'>PDF</a>, and <a href='""" + WEB_URL + """'>Web</a> 
                  <strong>GPT-4 data</strong> (created after training cutoff).
                  <ul style="list-style-type:square;">
                  <li>Set "Retrieval Augmented Generation" to "<strong>False</strong>" and submit prompt "What is GPT-4?" The LLM <strong>without</strong> RAG does not know the answer.</li>
                  <li>Set "Retrieval Augmented Generation" to "<strong>True</strong>" and submit prompt "What is GPT-4?" The LLM <strong>with</strong> RAG knows the answer.</li>
-                 <li>Experiment with prompts, e.g. "What are GPT-4's exam capabilities?" or "What is the cost and rate limit of the GPT-4 API? Answer in English and German in JSON format."</li>
-                 <li>Experiment more, for example "Write a Python program calling the GPT-4 API." or "Write a Node.js program calling the GPT-4 API."</li>
+                 <li>Experiment with prompts, e.g. "What are GPT-4's exam capabilities?" or "Write a Python program calling the GPT-4 API."</li>
+                 <li>Experiment more, for example "What is the cost and rate limit of the GPT-4 API? Answer in English and German in JSON format."</li>
                  </ul>\n\n
                  <strong>Technology:</strong> <a href='https://www.gradio.app/'>Gradio</a> UI using <a href='https://openai.com/'>OpenAI</a> API via AI-first 
-                 <a href='https://www.langchain.com/'>LangChain</a> toolkit with <a href='""" + WEB_URL_1 + """'>GPT-4</a> foundation model and AI-native 
+                 <a href='https://www.langchain.com/'>LangChain</a> toolkit with <a href='""" + WEB_URL + """'>GPT-4</a> foundation model and AI-native 
                  <a href='https://www.trychroma.com/'>Chroma</a> embedding database."""
 
 gr.close_all()