Spaces:
Runtime error
Runtime error
File size: 2,155 Bytes
83c6c56 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
from langchain.document_loaders import YoutubeLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain import PromptTemplate
from langchain.chains import LLMChain
from dotenv import load_dotenv
# Initiating the dotenv
load_dotenv()
embeddings = OpenAIEmbeddings()
# A function to create a db using FAISS
def create_db_from_youtube_video_url(video_url: str) -> FAISS:
# Loading the video
loader = YoutubeLoader.from_youtube_url(video_url)
transcript = loader.load()
# Splitting the document into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
docs = text_splitter.split_documents(transcript)
# Saving the chunks into vector store
db = FAISS.from_documents(docs, embeddings)
return db
# A function to get the response from the query passed
def get_response_from_query(db, query, k=4):
"""
text-davinci-003 can handle up to 4097 tokens. Setting the chunksize to 1000 and k to 4 maximizes
the number of tokens to analyze.
"""
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="""
You are a helpful assistant that that can answer questions about youtube videos
based on the video's transcript.
Answer the following question: {question}
By searching the following video transcript: {docs}
Only use the factual information from the transcript to answer the question.
If you feel like you don't have enough information to answer the question, say "I don't know".
Your answers should be verbose and detailed.
""",
)
chain = LLMChain(llm=llm, prompt=prompt)
response = chain.run(question=query, docs=docs_page_content)
response = response.replace("\n", "")
return response, docs |