add app.py

app.py

@@ -0,0 +1,78 @@
+
+from langchain.document_loaders import YoutubeLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain.vectorstores import FAISS
+from dotenv import load_dotenv
+import gradio as gr
+from langchain.document_loaders import YoutubeLoader
+
+
+load_dotenv()
+
+embeddings = OpenAIEmbeddings()
+
+# video_url = "https://www.youtube.com/watch?v=PfTOr3ONKzU"
+def create_vector_db_from_youtube_url(video_url: str):
+    loader = YoutubeLoader.from_youtube_url(video_url)
+    transcript = loader.load()
+    
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    docs = text_splitter.split_documents(transcript)
+    
+    db = FAISS.from_documents(docs, embeddings)
+    return db
+
+
+
+
+# create_vector_db_from_youtube_url(video_url)
+
+def get_response_from_query(db, query, k=4):
+  docs = db.similarity_search(query, k=k)
+  docs_page_content = " ".join([d.page_content for d in docs])
+
+  llm = OpenAI(model_name="text-davinci-003")
+  prompt = PromptTemplate(
+      input_variables=["question", "docs"],
+      template = """
+      Youare a helpful Youtube assistant that can answer questions about videos based on video transcript.
+      
+      Answer the following question: {question}
+      By searching the following video transcript: {docs}
+
+      Only use the factua; information from the transcript to answer the question.
+
+      If you feel like you dont have enough information to answer the question, say "I dont know".
+
+      Your answer ahould be detailed.
+      """
+  )
+
+  chain = LLMChain(llm=llm, prompt=prompt)
+
+  response = chain.run(question = query, docs = docs_page_content)
+  response = response.replace("\n", " ")
+  return response
+
+
+def gradio_interface(youtube_url, query):
+    if query and youtube_url:
+        db = create_vector_db_from_youtube_url(youtube_url)
+        response = get_response_from_query(db, query)
+        return response
+
+# Membuat antarmuka Gradio
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=["text", "text"],  # Dua input teks: URL YouTube dan pertanyaan
+    outputs="text",          # Output berupa teks
+    title="YouTube Assistant",
+    description="Masukkan URL YouTube dan ajukan pertanyaan tentang video tersebut."
+)
+
+# Menjalankan antarmuka Gradio
+iface.launch()