Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by Som23Git • Uncategorized
An MCP server integrating Telegram, n8n, AWS Bedrock LLMs, and Elasticsearch for conversational data ingestion and querying.
Ingest structured expense data from conversational inputs including voice and text.
Perform semantic search queries over indexed data using natural language.
Orchestrate multi-step workflows integrating Telegram, speech-to-text, LLM classification, and Elasticsearch.
This system enables users to send voice or text messages via Telegram, which are transcribed, classified, and ingested into Elasticsearch using a structured JSON format with semantic search capabilities. It supports conversational queries over the ingested data through an AI query agent, providing natural language responses. The architecture leverages AWS Bedrock-hosted LLMs for intent classification, ingestion, and querying, orchestrated by n8n workflows, enabling a seamless conversational interface for managing and querying expense data.