📄️ Data Sources
Therix is a versatile tool designed to facilitate the integration of various data sources into your projects. Whether you're working with PDFs, CSV files, or even YouTube videos, Therix offers seamless integration, allowing you to harness data from diverse origins effortlessly. This documentation will guide you through the process of adding different data sources using Therix.
📄️ System Prompt
System prompt is a way of adding custom prompt to your language models that override the existing prompt provided by Therix.
📄️ Embedding Model
Therix provides an embedding layer for Large Language Model (LLM). Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.
📄️ Inference Model
Inference models are neural network architectures designed for natural language processing tasks. They analyze input text to generate responses, answer questions, make predections, or summarize content.
📄️ Caching
Therix provides an optional caching layer for Language Model (LM) requests. This caching layer offers two primary benefits:
📄️ Trace
Therix provides a tracing feature. Tracing acts like a detective tool for your Language Model (LM), helping understand what's happening, identifying the root cause of problems, and tracking the cost borne by different models based on tokens used. Additionally, it shows you a statistical representation of your Language Model (LM) usage.