ZenithAI ZenithAI

Private, governed AI for your enterprise.

Answers, documents and research on infrastructure you control. Your conversations and files stay inside your organisation.

  • Models run on your own servers; prompts are not sent to public AI providers.
  • Sign-in with your organisation’s one-time codes, with access limited to authorised users.
  • Document analysis, web research and Office output, with cited sources.
A product of Data Ingenious

Sign in to ZenithAI

Use your work email and the one-time code from your authenticator.

Codes come from the authenticator registered to your account.

https://zenithai.data.in ·by Data Ingenious Access is restricted to authorised users.
Chats
    Settings

    ZenithAI v4.5.ad76bc56

    Loading…
    Internet access is blocked while private context is active.
    Web search (all chats)
    Internet for this chat's private documents

    AI can make mistakes. Check important info.

    Prompt & features

    Changes save automatically where toggles apply

    Model & reasoning

    Default model for new chats

    Reasoning (step-by-step thinking before answering)

    ⓘ Reasoning improves answers with conditions, deadlines and eligibility rules, and adds a few seconds per answer.

    Details

    Settings are managed by the administrator in model_settings.cfg.

    About you

    Your info 0 / 1000 ✎ Editable

    Tell the assistant about yourself — your role, preferences, anything useful for it to know. This is added as context, not as your own system prompt. Your name from your profile (topbar → your email) is included automatically.

    System prompt

    Active prompt 🔒 View only 
    Loading…

    Knowledge base Retired

    This global knowledge store has been retired — use Workspaces instead for document uploads, a persona, and durable facts scoped to you.

    Web search (DDGS)

    Type #search to force, #nosearch to skip.

    Prompt spell-check

    Suggested follow-ups

    Each workspace gives its chats their own persona, facts and knowledge. ⚠ Any user of this box can open any workspace — don't store person-private data.

      New workspace

      Shown in chat headers and the workspace picker.

      Persona optional

      The role, tone and rules every chat in this workspace follows — like a standing instruction to the assistant. You can change it any time; leave blank for the standard behavior.

      Facts optional

        Short, durable truths injected into every chat here — rates, addresses, policies. ⚠ Visible to everyone using this workspace.

        Knowledge
        —

        Chats in this workspace automatically answer from these documents (and the Efix database when attached). Upload, check status and delete on the Knowledge screen — one place for all of it.

        Persona

        The role, tone and rules every chat here follows — like a standing instruction to the assistant. Leave blank for the standard behavior.

        Facts

          Short, durable truths injected into every chat — saved when someone says "remember …" in a workspace chat, or added here. ⚠ Visible to everyone using this workspace.

          Could not load organisation administration.

          You are not in an organisation yet. Organisations and their members are set up by the server admin. When you are added, your organisation appears here.

          Users in Organization
          Add people

          Type the full address of someone who already has a ZenithAI account; they join as a member. A DataGroup user who has never signed in to ZenithAI has no account yet: ask them to sign in once, or ask the server admin. If the server admin suspended this person's membership, adding them again makes them an active member. For privacy, the reply is the same whether or not the address has an account; check the list.

          Add members

          “Everyone” workspaces include every active member listed here.

          Shared workspaces

          Create one to add knowledge for the organisation.

            To add knowledge to this workspace, click Open knowledge, then ＋ Add documents or Build website knowledge.

            People with access

                Search the organisation's members and pick them to add. Organizational Managers always have access.

                Add knowledge to an organisation workspace:
                1. Open a workspace here (Open ›), then Open knowledge, or use Organisation Knowledge in the Settings menu and pick the workspace.
                2. ＋ Add documents for files (PDF, DOCX, XLSX, CSV, TXT, MD).
                3. For a site, go to Add knowledge from a public website and click Build website knowledge.
                Only the organisation's Organizational Managers can add or delete knowledge. Members with access can use it in chat.
                Templates & assets Server admin

                Official assets and reusable document templates for /org document creation.

                Digital asset
                Document template

                Assets

                NameTypeFile
                No assets uploaded yet.

                Templates

                NameTypeFile
                No templates uploaded yet.

                Its Organizational Managers change its name and members; the server admin or an Admin archives organisations.
                ＋

                Create a workspace first

                Connector knowledge belongs to a workspace. Create one, then return here to upload your organization’s documents.

                ?
                What works best
                • Text-layer PDFs and clearly structured DOCX files.
                • Markdown (.md) and plain-text notes work as-is.
                • Policies, product notes, procedures, reference data.
                • Scanned PDFs are OCR-processed automatically when OCR is available.
                • Legacy DOC, XLS and PPT must be resaved in modern formats.
                PDF · DOCX · XLSX · CSV · TXT · MD — up to 3 MB per file, 100 MB per workspace. You can drop files anywhere on the list below.
                Add knowledge from a public website

                Only public HTTP(S) pages on the same website are imported. Website text becomes workspace knowledge and stays subject to the same RAG and citation rules as uploaded documents.

                  NameStatusKnowledgeUpdatedSize
                    ↥

                    Drop documents here

                    or

                    PDF · DOCX · XLSX · CSV · TXT · MD
                    Up to 3 MB per file · 100 MB per workspace
                    INTEGRATIONS
                    Efix Database — database search Not attached Manage

                    Ask natural-language questions against the published Efix knowledge source from a Chat using this workspace.

                    REST API keys

                    Create keys for external apps, scripts, or other machines on your network. The local web UI on this PC does not need a key. Remote clients must send Authorization: Bearer <key> or X-API-Key: <key>.

                    Rate limit: 6 requests per minute per key.

                    Copy this key now — it will not be shown again:

                      POST /chat
Authorization: Bearer <your-key>
Content-Type: application/json

{"message": "Hello", "stream": true}

                      OpenAI-compatible endpoint — works with any OpenAI SDK by setting base_url to this site's address followed by /v1. 

                      POST /v1/chat/completions
Authorization: Bearer <your-key>
Content-Type: application/json

{"model": "Smart",
 "messages": [{"role": "system", "content": "You are an office document assistant."},
              {"role": "user", "content": "Rewrite this professionally: Sales were bad."}],
 "temperature": 0.3, "stream": true, "max_tokens": 1024}

model      a tier name listed by GET /v1/models (not a raw model id)
stream     true → text/event-stream, ends with: data: [DONE]
GET /v1/models lists the available tiers.

Text only. This endpoint has no access to workspace documents,
saved memory, chat history or web search — send everything you
want considered in "messages". It also does not add a date, so
include one yourself if the answer depends on it.

Limit: 5 requests/min and 2 concurrent streams per key.

                      Your API usage: last request per key

                      Requests made with your API keys. Last request per key only, not a full history. Chats in this app are not counted here; see Chat usage.

                      Key Last used IP Last prompt
                      Loading…

                      Your chat usage

                      Chats and workspace chats you had in this app: tokens generated per day and the biggest reply of each day. Requests made with your API keys are not counted here; see API usage.

                      Date Tokens generated Replies Biggest reply
                      Loading…

                      Egress audit — what left this machine

                      Every outbound web search is recorded here verbatim (after redaction) and kept forever — this is the audit record. You see your own searches plus unattributed API/automation traffic.

                      When Chat Provider Queries sent Hits
                      Loading…

                      All API keys

                      Every API key in this installation: who owns it, when it was last used and whether it may add documents. API use only: requests made with an API key. Most recently used first; keys never used are at the bottom. Never the secret, an IP address or prompt text. Chat use is not in this list: see Users, "Last seen" (last sign-in or chat).

                      The API keys could not be loaded right now. Try again in a moment.
                      /
                      Loading keys…J K move · Enter go to the switch
                      Name Prefix Owner Created Last API use Can add documents
                      Loading…

                      Switch on "Can add documents" to let that key add files to its owner's own personal workspaces through the API (POST /workspace/documents). Keys that are off can only read.

                      Top 10 by usage

                       

                      Live Snapshotlast 10 min

                      Live

                       

                      Overview

                      Loading…

                      Users

                      Search, filters, organisations, designation and each user's access settings.

                      Storage

                      Disk, chat attachments, what expires soon and where the space goes.

                      Google connection

                      API keys and usage

                      The list of every API key and the ten heaviest users moved to API & Usage.

                      Models

                      Model Backend Loaded Context VRAM Pinned
                      Loading…

                      System

                      Loading…
                      F
                      FRONTIER

                      Frontier Mode

                      ADMIN CONSOLE
                      Frontier settings
                      Today
                      Earlier
                      No earlier Frontier chats.
                      FRONTIER Chat
                      Budget: not configured
                      What are we creating?

                      Frontier can access configured external Frontier models, but it cannot access private workspaces or organization information.

                      Output Preview
                      Documents, decks, images, and long-form outputs will open here instead of crowding the chat.

                      Frontier output

                      Download file
                      Server admin External API connections

                      Frontier administration

                      Configure external model access and the people who are allowed to use it. Private workspaces and organization context stay outside Frontier.

                      User access

                      Grant Frontier access without granting access to private workspaces, tools, or organization context.

                      Loading users...
                      People 0 users
                      ACCESS POLICY

                      Select a user

                      Not configured
                      Allowed providers

                      Limit which configured provider APIs this user can call.

                      Capabilities

                      Chat is always available. Enable additional generation surfaces explicitly.

                      Token budget

                      Set the maximum token allowance for the selected period. Use 0 for no budget limit.

                      Select a person to configure their Frontier policy.

                      Model connections

                      Enable a provider to make it available in the Frontier model picker.

                      Loading provider settings...
                      Frontier uses only configured external provider APIs in this separate mode.
                      Create from this conversation

                      Your profile

                      This is who I act as on your behalf — how I introduce you on calls and sign letters. Only you can see it.

                      Chat log