📄️ AI Prompt Templates
Orkes Conductor enables you to create, refine, and securely share the prompts and utilize while building LLM based applications. This essential component of an AI application is managed with precise access controls, allowing you to determine which models they can be associated with and which teams can incorporate them into their workflows.
📄️ LLM Text Complete
A system task to predict or generate the next phrase or words in a given text based on the provided context.
📄️ LLM Generate Embeddings
A system task to generate embeddings from the input data provided. Embeddings are the processed input text converted into a sequence of vectors, which can then be stored in a vector database for retrieval later. You can use a model that was previously integrated to generate these embeddings.
📄️ LLM Store Embeddings
A system task responsible for storing the generated embeddings produced by the LLM Generate Embeddings task, into a vector database. The stored embeddings serve as a repository of information that can be later accessed by the LLM Get Embeddings task for efficient and quick retrieval of related data.
📄️ LLM Get Embeddings
A system task to retrieve numerical vector representations of words, phrases, sentences, or documents that have been previously generated or learned by the model. Unlike the process of generating embeddings (LLM Generate Embeddings task), which involves creating vector representations from input data, this task focuses on efficiently accessing pre-existing embeddings. This is particularly useful when you have already computed and stored embeddings and want to utilize them without regeneration.
📄️ LLM Index Document
A system task designed to index a provided document into a vector database for efficient search, retrieval, and processing at a later stage.
📄️ LLM Get Document
A system task to retrieve the content of the document provided and use it for further data processing using AI tasks.
📄️ LLM Index Text
A system task designed to index the provided text into a vector space for efficient search, retrieval, and processing at a later stage.
📄️ LLM Search Index
A system task to search the vector database or repository of vector embeddings of already processed and indexed documents to get the closest match. You can input a query that typically refers to a question, statement, or request made in natural language that is used to search, retrieve, or manipulate data stored in a database.
📄️ LLM Chat Complete
A system task to complete the chat query. It can be used to instruct the model's behavior accurately to prevent any deviation from the objective.