Kizuki RAG Ingest for LangChain
io.github.kizukidata/rag-ingest
YouTube transcripts (chunks, phrase search, most replayed moments), PDFs and web pages as Markdown.
client:LangChain
transport:streamable-http
Install Kizuki RAG Ingest in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"rag-ingest": {
"transport": "streamable_http",
"url": "https://mcp.apify.com?tools=fetch-actor-details,kizukidata/youtube-transcripts,kizukidata/pdf-to-markdown,kizukidata/url-to-markdown",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs