Embeddings
Generate vector embeddings for each record in a JSONL file using a configured AI provider.
Embeddings Search
Vectorize a query attribute on a JSON record so it can be searched against a vector store.
Batch Job
Submit a JSONL batch job to an AI provider and stream results back as a file.
Chat
Chat completion against a configured AI provider (OpenAI, Mistral, Anthropic, Gemini, Cohere, Moonshot, Scaleway AI, OpenRouter, DeepSeek), with optional conversation memory.
Chunker
Split JSONL records into smaller chunks using an LLM-driven chunking method.
Data Extractor
Turn documents into structured data conforming to a JSON Schema, using a configured AI provider.
Enricher
Add LLM-extracted fields (sentiment, entities, classifications, β¦) to every record of a JSONL file.
Filter
Keep or drop each record of a JSONL file based on a natural-language acceptance criterion evaluated by an LLM.
Fixed Chunker
Deterministically split text into fixed-size word chunks with optional overlap.
Knowledge Graph
Extract a knowledge graph (entities + relations) from documents or JSON records using an LLM.
LlamaParse
Parse a document with LlamaParse (LlamaIndex) and emit the structured result as a JSON file.
MCP Endpoint
Expose connected Virtual Tools as a Model Context Protocol (MCP) endpoint that external MCP clients can call.
Markdown Chunker
Split markdown text along heading boundaries into size-bounded chunks.
Mistral Batch
Submit a JSONL batch job to Mistral and stream results back as a file.
Mistral chat
Send message to mistral chat
Mistral embeddings
Generate embeddings
Mistral Gen Search vector
Generate embeddings search query
Mistral OCR
Run Mistral OCR on a document URL or file and emit page text plus optional structured annotations.
OpenAI Embeddings
Generate embeddings using OpenAI's embeddings API.
OpenAI Embeddings Search
Generate a single search vector via OpenAI's embeddings API.
Qdrant embeddings
Embed vector into Qdrant vector database
Qdrant Search
Search a Qdrant collection with a dense embedding query or hybrid (dense + sparse) retrieval.
Recursive Chunker
Deterministically split text by trying separators from coarsest to finest until chunks fit a size budget.
Reranker
Re-score and filter a list of candidate documents against a query using an LLM/reranker provider.
Virtual Agent
Run a tool-calling LLM agent that picks among connected Virtual Tools to satisfy a prompt.
Virtual Tool
Declare a tool callable by a Virtual Agent or exposed via an MCP Endpoint, with typed argument outputs.
Virtual Tool Result
Record a tool's outcome into a Virtual Agent conversation session, optionally letting the model phrase the answer back to the user.