# Autom Mate Local LLM API Report – Admin Orchestrator & Assistant Runtime

### **1. Executive Summary**

This report summarizes the current state of the **Admin Orchestrator API** and the **Assistant Runtime API** endpoints. The goal is to clearly identify which endpoints are **ready (OK)** and which are **in development (🛠)**, and to provide decision-makers with an operational roadmap.

* **Admin Orchestrator API** → Manages assistant lifecycle, enable/disable, and administrative operations.
* **Assistant Runtime API** → Manages runtime interactions with assistants, file and vector store operations, and observability.

Key takeaway for decision-makers: **core management and runtime endpoints are production-ready**, while observability (metrics & telemetry) is still under development.

***

### **2. Admin Orchestrator API**

*(Lifecycle & Control)*

**OK (Ready)**

* ✅ **POST** `/admin/assistants/auto` → Create assistant (auto-id)
* ✅ **POST** `/admin/assistants` → Create assistant (explicit)
* ✅ **GET** `/admin/assistants` → List assistants
* ✅ **GET** `/admin/assistants/{assistant_id}` → Retrieve assistant details
* ✅ **POST** `/admin/assistants/{assistant_id}/enable` → Enable assistant
* ✅ **POST** `/admin/assistants/{assistant_id}/disable` → Disable assistant
* ✅ **DELETE** `/admin/assistants/{assistant_id}` → Delete assistant

**🛠 In Development**

* 🛠 **POST** `/admin/assistants/{assistant_id}` → Update assistant (model/vector settings, etc.)
* 🛠 Health proxy endpoint → Admin-side health check

***

### **3. Assistant Runtime API**

*(Runtime, RAG & Observability)*

**OK (Ready)**

* ✅ **GET** `/health` → System health check
* ✅ **GET** `/version` → API/service version check
* ✅ **POST** `/assistants/{assistant_id}/ask` → Submit question (synchronous)
* ✅ **POST** `/assistants/{assistant_id}/stream` → Submit question (streaming)
* ✅ **GET/POST** `/assistants/{assistant_id}/sessions` → Create/list sessions
* ✅ **GET** `/assistants/{assistant_id}/users` → List users
* ✅ **POST** `/assistants/{assistant_id}/files` → Upload file
* ✅ **GET** `/assistants/{assistant_id}/files` → List files
* ✅ **DELETE** `/assistants/{assistant_id}/files/{file_id}` → Delete file
* ✅ **POST** `/assistants/{assistant_id}/vectorstores` → Create vector store
* ✅ **GET** `/assistants/{assistant_id}/vectorstores` → List vector stores

**🛠 In Development**

* 🛠 **GET** `/metrics` → System metrics (performance & load)
* 🛠 **GET** `/telemetry` → Telemetry information (detailed observability)

***

### **4. Strategic Takeaways**

* **Production-ready endpoints** → Core management, runtime interactions, and file/RAG processes are fully operational.
* **In-development endpoints** → Observability (metrics & telemetry) and the admin health proxy. Once completed, SLA management and scalability will be further reinforced.
* **Roadmap:**
  * **Short-term** → Current endpoints already support SLA-compliant operations.
  * **Mid-term** → Complete metrics & telemetry to strengthen system predictability.
  * **Long-term** → Integrate admin health proxy to enable automated traffic routing and failover.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.autommate.com/userguide/product-features/ai-agent-composer/autom-mate-local-llm-api-report-admin-orchestrator-and-assistant-runtime.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.