Refactoring: modular configuration, separated learning and response logic

src/chadgpt/chatbot.py

@@ -0,0 +1,10 @@
+from gpt_index import GPTSimpleVectorIndex
+from .config import DB_PATH
+
+
+def chatbot(input_text):
+    # TODO: need check if index_file no exist
+    index_file = DB_PATH + "/index.json"
+    index = GPTSimpleVectorIndex.load_from_disk(index_file)
+    response = index.query(input_text, response_mode="compact")
+    return response.response

src/chadgpt/config.py

@@ -0,0 +1,6 @@
+import os
+from dotenv import load_dotenv
+
+
+load_dotenv()
+DB_PATH = os.environ.get("DB_PATH", "/app/db")

src/chadgpt/indexer.py

@@ -0,0 +1,43 @@
+from langchain.chat_models import ChatOpenAI
+from gpt_index import (
+    SimpleDirectoryReader,
+    GPTSimpleVectorIndex,
+    LLMPredictor,
+    PromptHelper
+)
+
+
+def construct_index(db_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 = ChatOpenAI(
+        temperature=0.7,
+        model_name="gpt-3.5-turbo",
+        max_tokens=num_outputs
+    )
+
+    llm_predictor = LLMPredictor(llm)
+
+    # get documents for learn:
+    documents = SimpleDirectoryReader(db_path).load_data()
+
+    index = GPTSimpleVectorIndex(
+        documents,
+        llm_predictor=llm_predictor,
+        prompt_helper=prompt_helper
+    )
+
+    index_file = db_path + "/index.json"
+    index.save_to_disk(index_file)
+
+    return index

src/chadgpt/interface.py

@@ -0,0 +1,10 @@
+import gradio as gr
+from .chatbot import chatbot
+
+
+iface = gr.Interface(
+    fn=chatbot,
+    inputs=gr.components.Textbox(lines=7, label="Enter your text"),
+    outputs="text",
+    title="ISPsystem custom-trained AI Chatbot"
+)