Update app.py

app.py

@@ -1,48 +1,39 @@
-from llama_index import GPTVectorStoreIndex, SimpleDirectoryReader, LLMPredictor, ServiceContext, StorageContext, load_index_from_storage
-from langchain import OpenAI
-import gradio
+from gpt_index import SimpleDirectoryReader, GPTListIndex, GPTSimpleVectorIndex, LLMPredictor, PromptHelper, ServiceContext
+from langchain.chat_models import ChatOpenAI
+import gradio as gr
+import sys
 import os
 
 os.environ["OPENAI_API_KEY"] = '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'
 
 def construct_index(directory_path):
-    # set number of output tokens
-    num_outputs = 256
+    max_input_size = 4096
+    num_outputs = 512
+    max_chunk_overlap = 20
+    chunk_size_limit = 600
 
-    _llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.5, model_name="gpt-4", max_tokens=num_outputs))
+    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
 
-    service_context = ServiceContext.from_defaults(llm_predictor=_llm_predictor)
+    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.7, model_name="gpt-4", max_tokens=num_outputs))
 
-    docs = SimpleDirectoryReader(directory_path).load_data()
+    documents = SimpleDirectoryReader(directory_path).load_data()
 
-    index = GPTVectorStoreIndex.from_documents(docs, service_context=service_context)
-    
-    #Directory in which the indexes will be stored
-    index.storage_context.persist(persist_dir="indexes")
+    index = GPTSimpleVectorIndex(documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper)
+
+    index.save_to_disk('index.json')
 
     return index
 
 def chatbot(input_text):
-    
-    # rebuild storage context
-    storage_context = StorageContext.from_defaults(persist_dir="indexes")
-    
-    #load indexes from directory using storage_context 
-    query_engne = load_index_from_storage(storage_context).as_query_engine()
-    
-    response = query_engne.query(input_text)
-    
-    #returning the response
+    index = GPTSimpleVectorIndex.load_from_disk('index.json')
+    response = index.query(input_text, response_mode="compact")
     return response.response
 
-#Creating the web UIusing gradio
-iface = gradio.Interface(fn=chatbot,
-                     inputs=gradio.inputs.Textbox(lines=4, label="Enter your question here"),
-                     outputs=gradio.outputs.Textbox(label="Generated Text"),
-                     title="Custom-trained AI Chatbot")
+iface = gr.Interface(fn=chatbot,
+                     inputs=gr.components.Textbox(lines=7, label="Enter your text"),
+                     outputs="text",
+                     title="My Custom-trained AI Chatbot")
 
-#Constructing indexes based on the documents in trainingData folder
 index = construct_index("trainingData")
-
-#launching the web UI using gradio
 iface.launch()
+