Detail View
This module contains views to implement the LLMHost card-style detail view in the Smarter Dashboard.
- class smarter.apps.llmhost.views.detailview.LLMHostComputeDetailView(**kwargs)[source]
Bases:
LLMHostDetailViewRenders the manifest of an LLMHostCompute, with its node group’s status, in YAML.
Example usage:
GET /llmhost/compute/<hashed_id>/
- manifest_kind: SAMKinds = 'LLMHostCompute'
- model
alias of
LLMHostCompute
- class smarter.apps.llmhost.views.detailview.LLMHostDetailView(**kwargs)[source]
Bases:
DocsBaseViewRenders the detail view for a Smarter dashboard llmhost.
This view renders a detailed manifest for a specific llmhost, including its configuration and metadata, in YAML format. It is intended for authenticated users and provides error handling for missing or unsupported llmhost kinds and names.
- Parameters:
- Returns:
Rendered HTML page with llmhost manifest details, or a 404 error page if the llmhost is not found or parameters are invalid.
- Return type:
HttpResponse
Note
The llmhost name and kind must be provided and valid. Otherwise, a “not found” response is returned.
See also
LLMHostfor llmhost metadata retrieval.ApiV1CliDescribeApiViewfor API details.Example usage:
GET /llmhost/detail/?name=my_llmhost&kind=custom
- get(request, *args, **kwargs)[source]
Handle GET requests to render the llmhost manifest detail view.
This method processes the incoming request to retrieve the specified llmhost’s manifest details and renders them in a user-friendly format. It performs validation on the provided llmhost name and kind, retrieves the llmhost metadata, and handles any errors that may arise during this process.
Process: 1. Extract and validate ‘name’ and ‘kind’ from kwargs. 2. Retrieve the llmhost metadata using the provided name and user context. 3. If the llmhost is found, call the API view to get the llmhost details 4. Convert the JSON response to YAML format for better readability. 5. Render the llmhost manifest detail template with the retrieved data. 6. Handle any errors that occur during the process and return appropriate error responses.
- Parameters:
- Returns:
Rendered HTML page with llmhost manifest details, or an error response if the llmhost is not found or parameters are invalid.
- Return type:
- llmhost: LLMHost | LLMHostCompute | None = None
The resource whose manifest is rendered.
- manifest_kind: SAMKinds = 'LLMHost'
- model
The resource’s model.
The view finds it by hashed id, among the user’s, their account admin’s and the Smarter admin’s.
- Parameters:
id (Unknown) – Primary key: ID
created_at (Unknown) – Created at
updated_at (Unknown) – Updated at
name (Unknown) – Name. Name in camelCase, e.g., ‘apiKey’, no special characters.
description (Unknown) – Description. A brief description of this resource. Be verbose, but not too verbose.
version (Unknown) – Version. Semantic version in the format MAJOR.MINOR.PATCH, e.g., ‘1.0.0’.
annotations (Unknown) – Annotations. Key-value pairs for annotating this resource.
spec (Unknown) – Spec. The manifest’s spec, in camelCase. The source of truth for launching the LLMHost.
model_source (Unknown) – Model source
model_repository (Unknown) – Model repository. e.g. ‘meta-llama/Llama-3.1-8B-Instruct’, ‘llama3.1:8b’ or ‘s3://bucket/prefix’
model_revision (Unknown) – Model revision. Commit SHA, branch or tag pinned for reproducible deploys.
model_task (Unknown) – Model task
served_model_name (Unknown) – Served model name. The model name that clients send in their requests.
license (Unknown) – License
model_architecture (Unknown) – Model architecture. e.g. ‘llama’, ‘mistral’, ‘qwen3’
parameter_count (Unknown) – Parameter count
context_window (Unknown) – Context window
quantization (Unknown) – Quantization
embedding_dimensions (Unknown) – Embedding dimensions. Set only for embedding models.
supports_streaming (Unknown) – Supports streaming
supports_function_calling (Unknown) – Supports function calling
supports_vision (Unknown) – Supports vision
supports_reasoning (Unknown) – Supports reasoning
inference_engine (Unknown) – Inference engine
api_format (Unknown) – Api format
gpu_type (Unknown) – Gpu type. e.g. ‘A10G’
gpu_count (Unknown) – Gpu count. GPUs per replica.
vram_required_gb (Unknown) – Vram required gb
replicas (Unknown) – Replicas
cost_per_hour (Unknown) – Cost per hour. The cost per hour of one replica: its share of its compute’s node.
status (Unknown) – Status
status_message (Unknown) – Status message
is_active (Unknown) – Is active
ready_replicas (Unknown) – Ready replicas
endpoint_url (Unknown) – Endpoint url. The base URL inside the cluster.
public_url (Unknown) – Public url. The base URL of the Ingress, if any.
health_check_url (Unknown) – Health check url
last_health_check_at (Unknown) – Last health check at
last_health_ok (Unknown) – Last health ok
deployed_at (Unknown) – Deployed at. When the LLMHost was last launched.
Relationship fields:
- Parameters:
user_profile (Unknown) – User profile (related name:
llmhost)api_key_secret (Unknown) – Api key secret. The Smarter Secret with the API key that clients send as a Bearer token. (related name:
llmhosts)compute (Unknown) – Compute. The kind of node, and node group, that the LLMHost runs on: spec.compute. (related name:
llmhosts)tags (Unknown) – Tags. Tags for categorizing and organizing this resource. (related name:
llmhost)tagged_items (Unknown) – Tagged items (related name:
+)
Reverse relationships:
- Parameters:
events (Unknown) – All events of this llm host (related name of
llmhost)
alias of
LLMHost