LLMs

LLM management — generation-time model registration.

Namespace: Goodmem.Client.Api · Class: LlmsApi

Reach this surface as client.Llms on a GoodmemClient. Every network method is asynchronous — it returns a Task<T> (or an IAsyncEnumerable<T> for pagination and streaming) and accepts a CancellationToken; the Async suffix marks the standard .NET Task-based async pattern.

Methods

CreateAsync

Creates a new LLM configuration for text generation services. LLMs represent connections to different language model API services (like OpenAI, vLLM, etc.) and include all the necessary configuration to use them for text generation. DUPLICATE DETECTION: Returns HTTP 409 Conflict (ALREADY_EXISTS) if another LLM exists with identical {ownerId, providerType, endpointUrl, apiPath, modelIdentifier, credentialsFingerprint} after URL canonicalization. Uniqueness is enforced per-owner. Credentials are hashed (SHA-256) for uniqueness while remaining encrypted. The apiPath field defaults to '/chat/completions' if omitted. Requires CREATE_LLM_OWN permission (or CREATE_LLM_ANY for admin users).

Declaration

public Task<CreateLlmResponse> CreateAsync(LlmCreationRequest request, string? apiKey = null, CancellationToken ct = default)

HTTP — POST /v1/llms

Parameters

Returns

Task<CreateLlmResponse> — an awaitable that resolves to CreateLlmResponse.

Exceptions

Example

var resp = await client.Llms.CreateAsync(
    new LlmCreationRequest
    {
        DisplayName = "Doc LLM",
        ModelIdentifier = "gpt-4o-mini",
        Labels = new Dictionary<string, string> { ["env"] = "docs" },
    },
    "sk-..."
);
var llm = resp.Llm;
Console.WriteLine(llm.LlmId);

GetAsync

Retrieves the details of a specific LLM configuration by its unique identifier. Requires READ_LLM_OWN permission for LLMs you own (or READ_LLM_ANY for admin users to view any user's LLMs). This is a read-only operation with no side effects.

Declaration

public Task<LlmResponse> GetAsync(string id, CancellationToken ct = default)

HTTP — GET /v1/llms/{id}

Parameters

Returns

Task<LlmResponse> — an awaitable that resolves to LlmResponse.

Exceptions

Example

var llm = await client.Llms.GetAsync("your-llm-id");
Console.WriteLine(llm.DisplayName);

ListAsync

Retrieves a list of LLM configurations accessible to the caller, with optional filtering. LABEL FILTERS: Label filters accept either label.<key>=<value> or label[key]=value (for example, label.environment=production or label[environment]=production). PERMISSION-BASED FILTERING: With LIST_LLM_OWN permission, you can only see your own LLMs (ownerId filter is ignored if set to another user). With LIST_LLM_ANY permission, you can see all LLMs or filter by any ownerId. This is a read-only operation with no side effects.

Declaration

public Task<ListLlmsResponse> ListAsync(LlmsListOptions? options = null, CancellationToken ct = default)

HTTP — GET /v1/llms

Parameters

Returns

Task<ListLlmsResponse> — an awaitable that resolves to ListLlmsResponse.

Exceptions

Example

var resp = await client.Llms.ListAsync();
foreach (var llm in resp.Llms)
    Console.WriteLine($"{llm.LlmId} {llm.DisplayName}");

UpdateAsync

Updates an existing LLM configuration including display information, endpoint configuration, model parameters, credentials, and labels. All fields are optional - only specified fields will be updated. SUPPORTED_MODALITIES UPDATE: If the array contains >=1 elements, it replaces the stored set; if empty or omitted, no change occurs and it does not count as an update by itself. IMPORTANT: providerType is IMMUTABLE after creation and cannot be changed. Requires UPDATE_LLM_OWN permission for LLMs you own (or UPDATE_LLM_ANY for admin users).

Declaration

public Task<LlmResponse> UpdateAsync(string id, LlmUpdateRequest request, CancellationToken ct = default)

HTTP — PUT /v1/llms/{id}

Parameters

Returns

Task<LlmResponse> — an awaitable that resolves to LlmResponse.

Exceptions

Example

var updated = await client.Llms.UpdateAsync(
    "your-llm-id",
    new LlmUpdateRequest
    {
        DisplayName = "Doc LLM (updated)",
        MergeLabels = new Dictionary<string, string> { ["version"] = "2" },
    }
);
Console.WriteLine(updated.LlmId);

DeleteAsync

Permanently deletes an LLM configuration. This operation cannot be undone and removes the LLM record and securely deletes stored credentials. IMPORTANT: This does NOT invalidate or delete any previously generated content using this LLM - existing generations remain accessible. Requires DELETE_LLM_OWN permission for LLMs you own (or DELETE_LLM_ANY for admin users).

Declaration

public Task DeleteAsync(string id, CancellationToken ct = default)

HTTP — DELETE /v1/llms/{id}

Parameters

Returns

Task — completes when the operation finishes; there is no response body.

Exceptions

Example

await client.Llms.DeleteAsync("your-llm-id");

Data Models

Types in the Goodmem.Client.Models namespace. Each row lists the C# property, its type, the JSON wire name, and a description.

LLMCreationRequest

Request body for creating a new LLM. An LLM represents a configuration for text generation services.

LLMProviderType

LLM provider types

String enum: "OPENAI" · "LITELLM_PROXY" · "OPEN_ROUTER" · "VLLM" · "OLLAMA" · "LLAMA_CPP" · "CUSTOM_OPENAI_COMPATIBLE"

LLMCapabilities

Capabilities and features supported by an LLM service

LLMSamplingParams

Sampling and generation parameters for controlling LLM text output

CreateLLMResponse

Response containing the created LLM and any informational status messages

LLMResponse

LLM configuration information

ListLLMsResponse

Response containing a list of LLM configurations

LLMUpdateRequest

Request body for updating an existing LLM. All fields are optional - only specified fields will be updated. supportedModalities replaces the stored set only when the array contains at least one value; empty or omitted leaves it unchanged and does not count as an update by itself.