📄️ LLM Text Complete
The LLM Text Complete task generates text based on the provided prompt and LLM parameters.
📄️ LLM Generate Embeddings
The LLM Generate Embeddings task generates embeddings of the provided data.
📄️ LLM Store Embeddings
The LLM Store Embeddings task stores embeddings in a vector database.
📄️ LLM Get Embeddings
The LLM Get Embeddings task retrieves embeddings from a vector database.
📄️ LLM Index Document
The LLM Index Document task indexes a provided document into a vector database.
📄️ LLM Get Document
The LLM Get Document task retrieves the content of a provided document, which can be used for further data processing using AI tasks.
📄️ LLM Index Text
The LLM Index Text task indexes a provided text into a vector database.
📄️ LLM Search Index
The LLM Search Index task searches a vector database for relevant documents based on a query.
📄️ LLM Chat Complete
The LLM Chat Complete task is used instruct the LLM to behave in a certain manner.
📄️ Chunk Text
The Chunk Text task is used to split large text into smaller, structured segments for efficient processing and downstream analysis.
📄️ List Files
The List Files task lists files from cloud storage, Git repositories, or websites to enable organized access and downstream processing.
📄️ Parse Document
The Parse Document task is used to extract, convert, and chunk documents from multiple sources into Markdown format optimized for LLM and semantic processing.