API

An OpenAI-compatible API for living business knowledge.

Call EigenVertex like a language model. Get answers grounded in your corpus, graph, memory, citations and business rules.

A generalist model doesn’t know your sources, your decisions, your meetings, your constraints or your evidence. Every call starts from zero. EigenVertex adds the business-intelligence layer underneath the same call shape.

EigenVertex is not

  • A thin wrapper around someone else’s model.
  • A chatbot embedded in a widget.
  • A vector database with a search box on top.
  • A RAG demo that forgets context between calls.
  • A fine-tune you have to retrain every time the business changes.

EigenVertex is

  • A living domain-intelligence engine, callable like a model.
  • A sovereign AI application layer your teams actually control.
  • A surface familiar to anyone who has called an OpenAI-compatible API.
  • A way to ship serious business applications without training your own model.
  • A more governable, more confidential alternative to a bare LLM call.

Call EigenVertex exactly like you’d call an OpenAI-compatible endpoint. The shape is familiar. What comes back isn’t.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.eigenvertex.com/v1",
    api_key="EVTX_API_KEY"
)

response = client.chat.completions.create(
    model="eigenvertex/domain-intelligence",
    messages=[
        {"role": "user", "content": "What changed in this project since last briefing?"}
    ],
    extra_body={
        "workspace": "strategic-corpus",
        "scope": "project",
        "citations": True,
        "graph": True
    }
)
workspace Scopes the call to one corpus and its governance rules.
scope Narrows retrieval to a project, a session, or the whole workspace.
citations Returns the exact source passages behind the answer.
graph Lets the response traverse relationships, not just text.

Same call shape, run the way it would actually run in production: scoped to a workspace, routed through retrieval and reasoning controls, and shaped into a decision briefing rather than a paragraph of prose.

Request

from openai import OpenAI

evtx = OpenAI(
    base_url="https://api.eigenvertex.com/v1",
    api_key=os.environ["EVTX_API_KEY"],
)

response = evtx.chat.completions.create(
    model="eigenvertex/domain-intelligence",
    messages=[
        {
            "role": "system",
            "content": (
                "You are preparing a decision briefing for the executive team. "
                "Use citations, project memory, graph relationships and open questions."
            ),
        },
        {
            "role": "user",
            "content": (
                "What changed since the last briefing, what decisions are now blocked, "
                "and what should we review in tomorrow’s meeting?"
            ),
        },
    ],
    extra_body={
        "workspace": "piano-heritage",
        "scope": {
            "corpus": ["technical-documents", "meeting-notes"],
            "project": "supplier-transition-2026",
            "session": "weekly-steering",
        },
        "retrieval": {
            "vector": True,
            "graph": True,
            "temporal_memory": True,
            "parent_expansion": True,
            "rerank": {
                "provider": "jina",
                "model": "jina-reranker-v2-base-multilingual",
                "top_k": 8,
            },
        },
        "reasoning": {
            "canonical_query": True,
            "multi_query": True,
            "self_reflective_evidence_score": True,
            "minimum_evidence_score": 3,
        },
        "output": {
            "format": "decision_briefing",
            "include_citations": True,
            "include_open_questions": True,
            "include_action_items": True,
            "include_graph_paths": True,
        },
    },
)

print(response.choices[0].message.content)

Response

{
  "answer": "Three supplier risks changed since the last briefing...",
  "evidence_score": 4,
  "citations": [
    {
      "source": "Supplier review - June 2026.pdf",
      "page": 12,
      "chunk_id": "chk_8f1...",
      "quote": "Lead times increased from 6 to 11 weeks..."
    }
  ],
  "graph_paths": [
    {
      "from": "Supplier A",
      "relation": "blocks",
      "to": "September launch milestone"
    }
  ],
  "open_questions": [
    "Has finance approved the alternative supplier budget?",
    "Do we have updated delivery guarantees?"
  ],
  "action_items": [
    {
      "owner": "Procurement",
      "task": "Request updated lead time confirmation",
      "due": "2026-06-28"
    }
  ]
}

You call it like a model. What comes back is a governed, sourced, graph-aware business deliverable — an answer, an evidence score, citations down to the page and the quote, the graph paths behind it, the open questions it surfaces, and the action items it implies.

Corpora & documents Versioned, traced sources — the ground truth.
Qdrant vector evidence Semantic recall over passages and artefacts.
FalkorDB GraphRAG Relational retrieval across entities and decisions.
Graphiti temporal memory What was true, when, and what changed since.
Projects & sessions The work itself — meetings, briefs, threads.
Decisions & action items Causes, owners, evidence, open questions.
Artefacts Reports, decks, dossiers already produced.
Citations & provenance Every answer traceable back to its source.
Ask with citations Answers that point back to the exact source passage.
Retrieve and rerank Hybrid retrieval, scored and reordered for relevance.
Traverse the graph Follow relationships between entities and decisions.
Use project memory Carry context across sessions instead of resetting.
Generate reports Turn corpus and memory into a structured document.
Produce artefacts Briefs, slides, dossiers — not just chat replies.
Monitor changes Detect what is new and compare it to memory.
Trigger discovery loops Route a question to the right corpora automatically.

EigenVertex can sit as a governed layer between your applications, your data and the models you choose.

API keys & scoped workspaces Every call is bound to a workspace and a key.
Corpus-level access control Decide exactly what each integration can reach.
Private cloud or on-premise Managed hosting, private cloud, or your own stack.
Citations & provenance Nothing comes back unsourced.
Auditability & traceability Every result traces to a graph path and a source.
No silent fine-tuning Specialisation happens in the open, not inside a black box.
Optional model routing Choose or rotate the underlying model per workload.

Fine-tuning has its place — but it is often rigid, costly and hard to govern. EigenVertex specialises behaviour a different way: through corpora, graphs, temporal memory, retrieval strategy, agent orchestration, query rewriting, reranking, structured outputs, rules and scopes.

CorporaGraphsTemporal memoryRetrieval strategyLangGraph agentsQuery rewritingRerankingStructured outputsRules & scopes
Legal research assistant Statutes, case law and filings, cited and current.
Industrial knowledge assistant Technical references and field feedback, unified.
Financial intelligence dashboard Filings and signals reasoned over, not just indexed.
Meeting & project copilot A copilot that remembers the last briefing.
Scientific corpus explorer Literature linked to hypotheses and results.
Monitoring & news intelligence New signals compared against what you already know.
Customer support intelligence layer Support answers grounded in your real documentation.
Internal decision engine Decisions mapped to their evidence and their effects.
Publishing & reporting pipeline Corpus and memory turned into sourced deliverables.
Expert portal for clients A governed, citable expert surface for your clients.
EigenVertex is not another model endpoint. It is the intelligence layer your applications can call.