hive-system.gpu.ollama — io.github.hive-agi/hive-system 0.2.7

OllamaGpuExecutor — IGpuExecutor + IGpuStatus over the ollama HTTP API.

First concretion of hive-system.protocols.gpu. Mirrors hive-system.secrets/* placement: protocol in hive-system.protocols.*, concrete adapter in a sibling sub-namespace.

Capabilities: :embed — POST /api/embed :generate — POST /api/generate (single-shot, no streaming for now)

What we deliberately don't do here:

• Pool / retry classification — that's the caller's job via hive-weave.gpu/gpu-fork-join + hive-dsl rescue helpers.
• Streaming / SSE — generate returns once, no incremental delta.
• Model autoload — assumes ollama pull <model> already happened.

Construct via (->ollama-executor opts) — never the raw record ctor.

ollama-executor clj

(ollama-executor)

(ollama-executor {:keys [host default-model default-timeout-ms
                         connect-timeout-ms executor-id]
                  :or {host "http://localhost:11434"
                       default-model "nomic-embed-text"
                       default-timeout-ms 120000
                       connect-timeout-ms 30000
                       executor-id :ollama}})

Build an OllamaGpuExecutor.

Options: :host — base URL (default "http://localhost:11434") :default-model — model used when GpuRequest omits :gpu/model (default "nomic-embed-text") :default-timeout-ms — per-op HTTP timeout (default 120000) :connect-timeout-ms — TCP connect timeout (default 30000) :executor-id — keyword id (default :ollama)