Update app.py

app.py

@@ -1,7 +1,9 @@
 import gradio as gr
-import logging, os, sys, threading, time
+import logging, os, sys, threading
+import pandas as pd
 
 from dotenv import load_dotenv, find_dotenv
+from datasets import load_dataset
 
 lock = threading.Lock()
 
@@ -13,14 +15,6 @@ RAG_OFF        = "Off"
 RAG_NAIVE  = "Naive RAG"
 RAG_ADVANCED = "Advanced RAG"
 
-config = {
-    "chunk_overlap": 100,       # split documents
-    "chunk_size": 2000,         # split documents
-    "k": 2,                     # retrieve documents
-    "model_name": "gpt-4-0314", # llm
-    "temperature": 0            # llm
-}
-
 logging.basicConfig(stream = sys.stdout, level = logging.INFO)
 logging.getLogger().addHandler(logging.StreamHandler(stream = sys.stdout))
 
@@ -34,21 +28,23 @@ def invoke(openai_api_key, prompt, rag_option):
 
     with lock:
         os.environ["OPENAI_API_KEY"] = openai_api_key
-        
-#        if (RAG_INGESTION):
-#            if (rag_option == RAG_LANGCHAIN):
-#                #rag = LangChainRAG()
-#                #rag.ingestion(config)
-#            elif (rag_option == RAG_LLAMAINDEX):
-#                #rag = LlamaIndexRAG()
-#                #rag.ingestion(config)
-    
-        completion = ""
-        result = ""
-        callback = ""
-        err_msg = ""
 
+        ###
+        dataset = load_dataset("MongoDB/airbnb_embeddings", streaming=True, split="train")
+        dataset = dataset.take(100)
+        dataset_df = pd.DataFrame(dataset)
+        dataset_df.head(5)
+        ###
+        
         """
+        if (RAG_INGESTION):
+            if (rag_option == RAG_LANGCHAIN):
+                #rag = LangChainRAG()
+                #rag.ingestion(config)
+            elif (rag_option == RAG_LLAMAINDEX):
+                #rag = LlamaIndexRAG()
+                #rag.ingestion(config)
+    
         try:
                 #rag = LangChainRAG()
                 #completion, callback = rag.rag_chain(config, prompt)
@@ -68,24 +64,18 @@ def invoke(openai_api_key, prompt, rag_option):
             del os.environ["OPENAI_API_KEY"]
         """
 
-        return ""# result
+        return "TODO"
 
 gr.close_all()
 
 demo = gr.Interface(
     fn = invoke, 
     inputs = [gr.Textbox(label = "OpenAI API Key", type = "password", lines = 1), 
-              gr.Textbox(label = "Prompt", value = "List GPT-4's exam scores and benchmark results.", lines = 1),
+              gr.Textbox(label = "Prompt", value = "TODO", lines = 1),
               gr.Radio([RAG_OFF, RAG_NAIVE, RAG_ADVANCED], label = "Retrieval-Augmented Generation", value = RAG_ADVANCED)],
     outputs = [gr.Textbox(label = "Completion")],
     title = "Context-Aware Reasoning Application",
-    description = os.environ["DESCRIPTION"],
-    examples = [["sk-<BringYourOwn>", "What are GPT-4's media capabilities in 5 emojis and 1 sentence?", RAG_ADVANCED],
-                ["sk-<BringYourOwn>", "List GPT-4's exam scores and benchmark results.", RAG_ADVANCED],
-                ["sk-<BringYourOwn>", "Compare GPT-4 to GPT-3.5 in markdown table format.", RAG_ADVANCED],
-                ["sk-<BringYourOwn>", "Write a Python program that calls the GPT-4 API.", RAG_ADVANCED],
-                ["sk-<BringYourOwn>", "What is the GPT-4 API's cost and rate limit? Answer in English, Arabic, Chinese, Hindi, and Russian in JSON format.", RAG_ADVANCED]],
-               cache_examples = False
+    description = os.environ["DESCRIPTION"]
 )
 
 demo.launch()