Models & APIs
AI & LLMs glossary
AI features in mobile apps usually mean remote LLM APIs, structured prompts, usage limits, and clear non-advice disclaimers. This cluster defines terms from large language models and chat APIs to RAG, embeddings, fine-tuning, and token limits.
Use quick cards for team alignment and crawler context. In-depth guides explain the concepts you need before shipping coach chat, document Q&A, or multimodel workspaces — with quoted notes from Sych on production mobile integrations.
Connect glossary terms to the Prompt Library for workflow templates and to products like Sagittarius AI or Plant Doctor AI where LLM features ship under real store and privacy constraints.
In-depth guides in AI & LLMs
In-depth guide
Large Language Model
A large language model (LLM) is a neural network trained on vast text to predict the next token — enabling chat, summarization, classification, and code generation via API or on-device models.
Read full guideIn-depth guide
Embeddings Model
An embeddings model converts text into a numeric vector so similar meanings sit close together — powering semantic search, recommendations, and RAG retrieval.
Read full guideIn-depth guide
RAG Retrieval Augmented Generation
Retrieval augmented generation (RAG) retrieves relevant snippets from your data, then asks an LLM to answer using that context — reducing hallucinations versus pure chat.
Read full guideIn-depth guide
Fine-Tuning LLM
Fine-tuning continues training a base LLM on your dataset so outputs match domain tone or format — heavier than prompts or RAG alone.
Read full guideIn-depth guide
Token Limit
Token limits define how much text (input + output) an LLM request can handle — affecting cost, latency, and whether your full document fits in one call.
Read full guideAll terms in AI & LLMs
Showing 1–15 of 54 terms · page 1 of 4
AI & LLMs
GuideLarge Language Model
A large language model (LLM) is a neural network trained on vast text to predict the next token — enabling chat, summarization, classification, and code generation via API or on-device models.
Read full guideAI & LLMs
GPT-4o
GPT-4o is an AI and LLM concept for building multimodal features on OpenAI's GPT-4o model family so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Claude Model
Claude Model is an AI and LLM concept for integrating Anthropic Claude models for long-context and safety-sensitive tasks so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Gemini Model
Gemini Model is an AI and LLM concept for calling Google Gemini models for text, code, and vision workloads so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
OpenAI API
OpenAI API is an AI and LLM concept for accessing OpenAI models through authenticated HTTP APIs from your backend so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Chat Completions API
Chat Completions API is an AI and LLM concept for sending role-based message arrays to generate assistant replies so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Responses API OpenAI
Responses API OpenAI is an AI and LLM concept for using OpenAI's Responses API for stateful agent-style interactions so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Assistants API
Assistants API is an AI and LLM concept for managing persistent assistants with files, tools, and thread history so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
GuideEmbeddings Model
An embeddings model converts text into a numeric vector so similar meanings sit close together — powering semantic search, recommendations, and RAG retrieval.
Read full guideAI & LLMs
Vector Embedding
Vector Embedding is an AI and LLM concept for representing meaning as numeric vectors for nearest-neighbor lookup so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Semantic Search
Semantic Search is an AI and LLM concept for finding content by meaning rather than exact keyword overlap so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
GuideRAG Retrieval Augmented Generation
Retrieval augmented generation (RAG) retrieves relevant snippets from your data, then asks an LLM to answer using that context — reducing hallucinations versus pure chat.
Read full guideAI & LLMs
Chunking Strategy RAG
Chunking Strategy RAG is an AI and LLM concept for splitting documents into retrieval-friendly segments with overlap and metadata so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Vector Database
Vector Database is an AI and LLM concept for indexing embeddings for fast approximate nearest-neighbor search at scale so product teams ship reliable intelligence features faster.
Read definitionAI & LLMs
Pinecone
Pinecone is an AI and LLM concept for hosting managed vector indexes for RAG and recommendation workloads so product teams ship reliable intelligence features faster.
Read definitionSagittarius AI routes tasks across multiple LLMs in one mobile workspace — chat, files, and vision.
Sagittarius AIMultimodel AI workspace — chat, file analysis, vision, and image generation. Android and iOS, closed testing.View productExplore topics related to Large Language Model
AI workflows
Prompt Engineering
How to structure prompts, variables, outputs, and reusable AI workflows.
Server stack
Backend & Firebase
Firebase, Postgres, serverless APIs, auth, and mobile backend infrastructure terms.
Build & grow
Product & Startup
MVP, metrics, monetization strategy, and indie product vocabulary.