{"version":1,"pages":[{"id":"yZYPrGB6HezXKPKYOzlX","title":"Introduction","pathname":"/","siteSpaceId":"sitesp_2MvNv","description":"Welcome to the official THub documentation."},{"id":"bJzNHGwymE20AYZaOqRj","title":"🔗 LangChain","pathname":"/langchain","siteSpaceId":"sitesp_2MvNv","description":"LangChain is an open-source framework designed to simplify the process of building applications powered by Large Language Models (LLMs). Here's a breakdown of what LangChain offers:"},{"id":"NVN2iJhsghMHLgWUD9h0","title":"🕵️ Agents","pathname":"/langchain/agents","siteSpaceId":"sitesp_2MvNv","description":"Autonomous AI components that dynamically select and use tools to solve complex tasks based on user inputs.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"JEsyoRGuzvXBiBN4idhu","title":"🗄️Cache","pathname":"/langchain/cache","siteSpaceId":"sitesp_2MvNv","description":"Caching can save you money by reducing the number of API calls you make to the LLM provider, if you're often requesting the same completion multiple times.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"1PnlZutFPax77KpbZ9vB","title":"⛓️Chains","pathname":"/langchain/chains","siteSpaceId":"sitesp_2MvNv","description":"In the context of chatbots and large language models, \"chains\" typically refer to sequences of text or conversation turns. These chains are used to store and manage the conversation history.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"EpDPo10k2Qg6UekiQOgG","title":"🗨️Chat Models","pathname":"/langchain/chat-models","siteSpaceId":"sitesp_2MvNv","description":"Chat models take a list of messages as input and return a model-generated message as output.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"zLiuXLsPWGPdFkyZ4CGa","title":"📁Document Loaders","pathname":"/langchain/document-loaders","siteSpaceId":"sitesp_2MvNv","description":"Document loaders allow you to load documents from different sources like PDF, TXT, CSV, Notion, Confluence etc. They are often used together with Vector Stores to be upserted as embeddings.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"TMgoGQyjpz6JfXsKXESH","title":"🧬Embeddings","pathname":"/langchain/embeddings","siteSpaceId":"sitesp_2MvNv","description":"Embeddings can be used to create a numerical representation of textual data. This numerical representation is useful because it can be used to find similar documents.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"i00PTwK7wvdpfW31dOnc","title":"Graph","pathname":"/langchain/graph","siteSpaceId":"sitesp_2MvNv","icon":"chart-mixed-up-circle-currency","description":"A Graph is a canvas where you can assemble various nodes to define the flow of data and operations. Each node represents a distinct operation, such as data input, processing,decision-making,or output.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"pMKDuKdUJHHii4l760lI","title":"🧠Large Language Models(LLM)","pathname":"/langchain/large-language-models-llm","siteSpaceId":"sitesp_2MvNv","description":"LLMs are advanced AI systems designed to understand and generate human language. They are trained on vast amount of data and can perform a variety of language-related tasks with impressive accuracy.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"kUI2QwLyquoUQlEDoGmu","title":"💾Memory","pathname":"/langchain/memory","siteSpaceId":"sitesp_2MvNv","description":"Memory allows you to chat with AI as if AI has the memory of previous conversations.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"BY837fJojpe4fbEFIoVQ","title":"🛡️Moderation","pathname":"/langchain/moderation","siteSpaceId":"sitesp_2MvNv","description":"Moderation nodes are used to check whether the input or output consists of harmful or inappropriate content.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"bRkxTp0pzIKhwvt4hmo8","title":"👥Multi Agents","pathname":"/langchain/multi-agents","siteSpaceId":"sitesp_2MvNv","description":"multiple independent actors powered by language models connected in a specific way.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"01u7r4tWjINvDWIj6cBo","title":"🔀Output Parsers","pathname":"/langchain/output-parsers","siteSpaceId":"sitesp_2MvNv","description":"An output parser acts as a translator between LLMs and your application. It takes the raw, unformatted text generated by an LLM and transforms it into a more usable format suited for your needs.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"0M3DIle6Ga0VhGnsLTIL","title":"📝Prompts","pathname":"/langchain/prompts","siteSpaceId":"sitesp_2MvNv","description":"A text input or instruction given to an AI model to guide its response. It serves as the context and directive for the AI, shaping the output by providing specific information, questions or tasks.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"VgFSjJYPhGu7Xg7cFbNf","title":"📊Record Managers","pathname":"/langchain/record-managers","siteSpaceId":"sitesp_2MvNv","description":"Record Managers keep track of your indexed documents, preventing duplicated vector embeddings in Vector Store.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"hh94SmfI1JPN8oXLIfnO","title":"Retrieval-Augmented Generation","pathname":"/langchain/retrieval-augmented-generation","siteSpaceId":"sitesp_2MvNv","emoji":"1f4d1","description":"The Ultimate Guide to Retrieval-Augmented Generation (RAG)","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"Sizd6SjWbayAzNuGSD8I","title":"🔍Retrivers","pathname":"/langchain/retrivers","siteSpaceId":"sitesp_2MvNv","description":"AI components that efficiently fetch relevant data from knowledge bases in response to queries, supporting natural language tasks like question-answering and information retrieval.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"17aD4gzbr6VYraYYznJz","title":"Sequential Agent","pathname":"/langchain/sequential-agent","siteSpaceId":"sitesp_2MvNv","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"mNP4N7HfhZ2NdlcoxZne","title":"✂️Text Splitters","pathname":"/langchain/text-splitters","siteSpaceId":"sitesp_2MvNv","description":"When you want to deal with long pieces of text, it is necessary to split up that text into chunks.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"s18XU9nf3HHr7tZlIiN2","title":"🛠️Tools","pathname":"/langchain/tools","siteSpaceId":"sitesp_2MvNv","description":"Tools are functions that agents can use to interact with the world. These tools can be generic utilities (e.g. search), other chains, or even other agents.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"b0Aip4gmZsBfQyz5ZWfS","title":"🔌Tools (MCP)","pathname":"/langchain/tools-mcp","siteSpaceId":"sitesp_2MvNv","description":"","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"VC8L9XteZzUrjhRuwCeF","title":"🗃️Vector Stores","pathname":"/langchain/vector-stores","siteSpaceId":"sitesp_2MvNv","description":"A vector store is a specialized database for storing and retrieving high-dimensional numerical vectors. It efficiently manages and indexes these vectors for fast similarity searches.","breadcrumbs":[{"label":"🔗 LangChain"}]},{"id":"7qu2TkY5bi6VwDtagZNQ","title":"🦙LLama Index","pathname":"/llama-index","siteSpaceId":"sitesp_2MvNv","description":"LlamaIndex is a data framework designed to work with large language models (LLMs)"},{"id":"THy0JcpKUBDVIrlIcE7o","title":"🕵️ Agents","pathname":"/llama-index/agents","siteSpaceId":"sitesp_2MvNv","description":"Autonomous AI components that dynamically select and use tools to solve complex tasks based on user inputs.","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"dvIsUZtywOhKZsaUMjNi","title":"🗨️Chat Models","pathname":"/llama-index/chat-models","siteSpaceId":"sitesp_2MvNv","description":"Chat models take a list of messages as input and return a model-generated message as output.","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"HViCTNcScYYenuZPBQqY","title":"🧬Embeddings","pathname":"/llama-index/embeddings","siteSpaceId":"sitesp_2MvNv","description":"Embeddings can be used to create a numerical representation of textual data. This numerical representation is useful because it can be used to find similar documents.","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"h58MDF971pGsxgDJa9Mx","title":"🚀Engine's","pathname":"/llama-index/engines","siteSpaceId":"sitesp_2MvNv","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"TsDzQqZggPqFMV6bpPAa","title":"🧪Response Synthesizer","pathname":"/llama-index/response-synthesizer","siteSpaceId":"sitesp_2MvNv","description":"Response Synthesizer nodes are responsible for sending the query, nodes, and prompt templates to the LLM to generate a response. There are 4 modes for generating a response:","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"xHbEhfm1tFS5npwoieOm","title":"🛠️Tools","pathname":"/llama-index/tools","siteSpaceId":"sitesp_2MvNv","description":"Tools are functions that agents can use to interact with the world. These tools can be generic utilities (e.g. search), other chains, or even other agents.","breadcrumbs":[{"label":"🦙LLama Index"}]},{"id":"BgBAZs4Ldc4UpS2PfK1w","title":"🗃️Vector Stores","pathname":"/llama-index/vector-stores","siteSpaceId":"sitesp_2MvNv","description":"A vector store is a specialized database for storing and retrieving high-dimensional numerical vectors. It efficiently manages and indexes these vectors for fast similarity searches.","breadcrumbs":[{"label":"🦙LLama Index"}]}]}