Update app.py

app.py

@@ -1,15 +1,46 @@
+from gpt_index import SimpleDirectoryReader, GPTListIndex, GPTSimpleVectorIndex, LLMPredictor, PromptHelper
+#from langchain.schema import BaseLanguageModel
+from langchain.chat_models import ChatOpenAI
 import gradio as gr
-from transformers import pipeline
+import sys
+import os
+import openai
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+os.environ["OPENAI_API_KEY"] = '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'
 
-def predict(image):
-    predictions = pipeline(image)
-    return {p["label"]: p["score"] for p in predictions}
+messages = [
+    {"role": "system", "content": "You try to be secretive but are terrible at it."},
+]
 
-gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
-    outputs=gr.outputs.Label(num_top_classes=2),
-    title="Hot Dog? Or Not?",
-).launch()
+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="Hello, I'm a wiG, what would you like to know?"),
+                     outputs="text",
+                     title="wiGs explained custom-trained AI Chatbot")
+
+index = construct_index("docs")
+iface.launch(share=True)