Update app.py

app.py

@@ -1,47 +1,38 @@
+from gpt_index import SimpleDirectoryReader, GPTListIndex, GPTSimpleVectorIndex, LLMPredictor, PromptHelper
+from langchain.chat_models import ChatOpenAI
 import gradio as gr
+import sys
 import os
-import openai
-from langchain.chains import ConversationalRetrievalChain
-from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import DirectoryLoader
-from langchain.indexes.vectorstore import VectorStoreIndexWrapper
-from langchain.indexes import VectorstoreIndexCreator
-from langchain.llms import OpenAI
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores.chroma import Chroma
-
-os.environ["OPENAI_API_KEY"] = "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"
-
-PERSIST = False
-
-if PERSIST and os.path.exists("persist"):
-    print("Reusing index...\n")
-    vectorstore = Chroma(persist_directory="persist", embedding_function=OpenAIEmbeddings())
-    index = VectorStoreIndexWrapper(vectorstore=vectorstore)
-    index.load("persist")
-else:
-  loader = DirectoryLoader("data/")
-  if PERSIST:
-    index = VectorstoreIndexCreator(vectorstore_kwargs={"persist_directory":"persist"}).from_loaders([loader])
-  else:
-    index = VectorstoreIndexCreator().from_loaders([loader])
-
-chain = ConversationalRetrievalChain.from_llm(llm=ChatOpenAI(model="gpt-3.5-turbo"), retriever=index.vectorstore.as_retriever(search_kwargs={"k": 1}))
-
-chat_history = []
-
-def answer_question(question):
-    global chat_history
-    result = chain({"question": question, "chat_history": chat_history})
-    chat_history.append((question, result['answer']))
-    return result['answer']
-
-iface = gr.Interface(
-    fn=answer_question,
-    inputs="text",
-    outputs="text",
-    title="SPARCBot",
-    description="Ask a question to get answers about your sparc data"
-)
 
+os.environ["OPENAI_API_KEY"] = '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'
+
+def construct_index(directory_path):
+    max_input_size = 4096
+    num_outputs = 512
+    max_chunk_overlap = 20
+    chunk_size_limit = 600
+
+    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
+
+    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=num_outputs))
+
+    documents = SimpleDirectoryReader(directory_path).load_data()
+
+    index = GPTSimpleVectorIndex(documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper)
+
+    index.save_to_disk('index.json')
+
+    return index
+
+def chatbot(input_text):
+    index = GPTSimpleVectorIndex.load_from_disk('index.json')
+    response = index.query(input_text, response_mode="compact")
+    return response.response
+
+iface = gr.Interface(fn=chatbot,
+                     inputs=gr.components.Textbox(lines=7, label="Enter your text"),
+                     outputs="text",
+                     title="Custom-trained AI Chatbot")
+
+index = construct_index("data")
 iface.launch(share=True)