upload app

app.py

@@ -1,7 +1,54 @@
 import gradio as gr
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from openai import OpenAI
 
-def greet(name):
-    return "Hello " + name + "!!"
+YOUR_OPENAI_API_KEY = "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"
+# 임베딩 모델 로드
+embedding_model_name = "snunlp/KR-SBERT-V40K-klueNLI-augSTS"
+embedding_model = HuggingFaceEmbeddings(
+    model_name=embedding_model_name,
+    encode_kwargs={"normalize_embeddings": True},
+)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+# vector DB 로드드
+save_path = "./my_faiss_index"
+vectorstore = FAISS.load_local(save_path, embedding_model,allow_dangerous_deserialization=True)
+retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+
+
+
+def chatbot(input_question):
+    basic_docs = retriever.invoke(input_question)
+    context = "\n".join([doc.page_content for doc in basic_docs])  
+
+    client = OpenAI(
+    api_key=YOUR_OPENAI_API_KEY)
+
+    # question과 context를 message에 삽입
+    completion = client.chat.completions.create(
+        model="gpt-4o-mini",  
+        messages=[
+            {
+                "role": "user",
+                "content": f"""당신은 반도체와 차세대반도체학과에 대해서 설명하는 Assistant입니다.
+    차세대반도체학과는 한국 서울의 중앙대학교의 창의ICT공과대학에 설립된 학과입니다. 
+    다음 맥락에 맞게 질문에 답하세요.
+
+    맥락: {context}
+
+    질문: {input_question}
+    """
+            }
+        ]
+    )
+
+
+
+    return completion.choices[0].message.content
+
+
+
+
+demo = gr.Interface(fn=chatbot, inputs="text", outputs="text")
 demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+langchain==0.3.13
+openai==1.58.1