from rag_code import EmbedData, QdrantVDB, new_faq_text
# Etapa 1: gerar embeddings dos textos do FAQ
embedder = EmbedData()
embedder.embed(contexts=new_faq_text)
# Etapa 2: conectar ao Qdrant e criar a coleção (se necessário)
vector_db = QdrantVDB("ml_faq_collection")
vector_db.create_collection()
# Etapa 3: inserir os vetores no Qdrant
vector_db.ingest_data(embedder)
print("✅ Coleção 'ml_faq_collection' populada com sucesso no Qdrant.")
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sandovalmedeiros/mcp_agentic_rag'
If you have feedback or need assistance with the MCP directory API, please join our Discord server