initial commit

app.py

@@ -1,63 +1,73 @@
+import json
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import pandas as pd
+
+from openai import OpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+
+
+MODEL = "gpt-4o"
+API_KEY = "sk-proj-FV9lzQDevcA7M7yllkL7T3BlbkFJgjk8JBewp08UwSFJwaXD"
+# BASE_URL = "https://youtu.be/"
+
+client = OpenAI(api_key = API_KEY)
+embeddings = OpenAIEmbeddings(model = "text-embedding-3-large", api_key = API_KEY)
+yt_chunks = FAISS.load_local("vector-large", embeddings, allow_dangerous_deserialization = True)
+df = pd.read_csv("../data/ko-youtube-trans-U10k.csv")
+
+def find_docs(message):
+    
+    finding_docs = yt_chunks.similarity_search(message, k = 5)
+    
+    indices = [doc.metadata['row'] for doc in finding_docs]
+    
+    retrievers = [json.loads(df.loc[idx].to_json(force_ascii = False)) for idx in indices]
+    
+    return retrievers
+
+def predict(message, history):
+    
+    openai_input = list()
+    
+    retriever = find_docs(message)
+    
+    system_prompt = """- You are an AI chat bot that recommends YouTube content to users as an assistant.\n- You were created and powered by 'bigster (빅스터)', an AI & bigdata expert company.\n- Recommend YouTube content to users based on what's in “retriever”.\n- If the user's question is not related to content recommendations, please display a message declining to answer.\n- You must recommend at least 3 YouTube content items to the user based on the information in the 'retriever'. Be sure to explicitly include 'url' & 'videoChannelName' & 'videoName' information in your response. Also, for each featured piece of content, summarize what's in the 'transcription' and present it to the user. Use the following Markdown format to create hyperlinks: '[videoName](url)'\n\n retriever:\n{retriever}"""
+    
+    for human, assistant in history:
+        openai_input.append({"role": "user", "content": human})
+        openai_input.append({"role": "assistant", "content": assistant})
+        
+    openai_input = [item for item in openai_input if item['role'] != "system"]
+    
+    openai_input.append({"role": "system", "content": system_prompt.format(retriever = retriever)})
+    openai_input.append({"role": "user", "content": message})
+    
+    response = client.chat.completions.create(
+        model = MODEL,
+        messages = openai_input,
+        temperature = 1.0,
+        stream = True
+    )
+
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+              partial_message = partial_message + chunk.choices[0].delta.content
+              yield partial_message
+
+    print(openai_input)
+    
+gr.ChatInterface(
+    predict, 
+    title = "YOUTUBE REC",
+    theme = gr.themes.Soft(primary_hue = "purple"),
+    examples = [
+        "네 이름은 뭐야?",
+        "파이썬 프로그래밍 언어를 독학하기 위한 영상을 추천해줘.",
+        "인간관계에서 큰 상실감을 느끼는 나를 위한 영상을 추천해줘.",
+        "간단하고 초보자도 이해하기 쉬운 딥러닝 강의 추천해줘.",
+        "프랑스 역사에 대해 공부하고 싶어요. 프랑스 역사에 관련된 다큐멘터리, 강의 영상을 추천해주세요.",
+        "요즘 에세이를 작성하고 ��습니다. 보다 효과적으로 글을 써내려가는 방법을 제시해주는 영상을 추천해주세요."
+    ]
+).launch(share = True, auth = ("user", "bigster123"))