Catalog
Connect 1C to Gleyk
A step-by-step wizard for connecting a 1C base through OData: where 1C runs, publishing on a web server, the user, entering the address in Gleyk and checking.
Deploy Gleyk on-prem
A step-by-step installation wizard: Docker Compose or Kubernetes, your own GPU with vLLM or an external API through a gateway, Elasticsearch or Infinity, launch and verification.
Agents on the canvas
The components of the visual builder, variables, test runs and debugging, templates, scheduled automations and confirming actions in Telegram.
API key and SDK
How to get an API key, the /api/v1 base address, Bearer authorization, the main methods for knowledge bases, documents, assistants and sessions, and a Python SDK example.
Platform architecture
Sources and connectors, processing and index, search, protection and permissions, a model in your perimeter or through a gateway, agents, automations, MCP and audit: how Gleyk is built.
Chat with sources
How to ask an assistant a question, read an answer with links to document fragments, open a source and what to do when no answer is found.
Connecting a 1C base through OData
Publishing the base on a web server, turning on OData, a separate user with read rights, entering the address in Gleyk, what the connector reads and how to handle typical errors.
Enterprise AI for business: what it is and how to implement it
What enterprise AI is, how it differs from a general AI chat, why the model stays yours to choose — and where to start implementation.
Installing Gleyk on-prem: overview
Requirements, the component set, choosing between Docker Compose and Kubernetes, where to place the GPU server with the model and where to get the full installation guide.
What is a knowledge base
What a knowledge base in Gleyk consists of: documents, chunks, an embedding model and an index; how to create a base, who sees it and how an assistant works with several bases.
Research mode: investigating across several sources
How the assistant builds a plan, runs tasks in the background, shows progress and returns a report with a source legend. How long it takes.
Organizations, roles and access
How organizations (tenants) are structured, the owner, administrator and user roles, the main administrator and the /admin console, SSO sign-in, permissions on knowledge bases and audit.
What is Gleyk
A platform for corporate knowledge and AI agents: knowledge bases, assistants with sources, agents on the canvas, automations, 1C and deployment inside your perimeter.
Documents and reports in chat
How to attach a PDF, Word or Excel file to a question, ask the assistant to prepare a report and where to find the files it creates.
Embedding a chat on a website
The "Embed into webpage" dialog, an iframe with shared_id and a beta token, public /chatbots endpoints, the SSE format and measures to protect the public token.
RAG vs general AI chat: when you need your own knowledge base
How RAG differs from a plain AI chat, when a chat is enough, and when business needs a corporate knowledge base with sources and permissions.
Uploading documents
Which files a knowledge base accepts, what processing does with PDF, Word, Excel, presentations and images, how to read statuses and progress messages, when to reprocess a document and where to view chunks.
Chunking methods and processing settings
Which chunking method to choose for each type of document, how chunk size, the delimiter and the PDF parser affect the result, and when to turn on Excel to HTML, auto-keywords, RAPTOR, the knowledge graph and PageRank.
MCP servers: tools for agents
What MCP is, how Gleyk uses MCP servers as a source of tools for agents, chat and research, the organization's server registry, the platform's built-in server and connecting external ones.
Private AI on-prem: when you cannot use the cloud
When business needs Private AI on-prem or private cloud: security requirements, sensitive data, air-gapped setups, and how to choose a deployment model.
AI assistant for customer support
How an AI assistant helps support teams: answers from the knowledge base, drafts, ticket routing and pilot KPIs.
Checking search on a knowledge base
The "Retrieval testing" tab: similarity threshold, keyword and vector weight, Top-K, reranker, how to read the scores of found chunks, typical causes of poor search and the check to run before connecting a base to an assistant.
AI assistant for information security
How AI helps security teams: threat modelling, vulnerability triage, regulatory search and certification prep on a knowledge graph.
Metadata, tags and PageRank
Document metadata and filtering by it in assistants and the API, tag sets for automatic labeling of chunks, the PageRank of a base, and how all of this is set in the interface and through the API.
AI assistant for legal teams
How an AI assistant helps legal teams: contract analysis, precedent search, compliance checks and work with internal opinions.
Knowledge base access and sharing between organizations
Who in an organization sees and changes a knowledge base, what the owner, the administrator and the main administrator do, how to give another organization read-only access to a base, how to revoke it and what goes into the audit.
Connectors and sync
Which sources connect to a knowledge base automatically, how credentials and OAuth are stored, what a full load and a polling interval are, pause and resume, deletions in the source, SharePoint specifics and typical errors.