58 lines
1.9 KiB
JavaScript
58 lines
1.9 KiB
JavaScript
const DEFAULT_URL = "http://localhost:11434";
|
|
|
|
export class Ollama {
|
|
constructor({ url = DEFAULT_URL, timeoutMs = 600000 } = {}) {
|
|
this.url = url.replace(/\/$/, "");
|
|
this.timeoutMs = timeoutMs;
|
|
}
|
|
|
|
async ping({ timeoutMs = 30000 } = {}) {
|
|
if (process.env.OLLAMA_SKIP_PING === "1") return { ok: true, model: process.env.OLLAMA_MODEL };
|
|
const res = await fetch(`${this.url}/api/tags`, { signal: AbortSignal.timeout(timeoutMs) });
|
|
if (!res.ok) throw new Error(`Ollama not reachable (HTTP ${res.status}) at ${this.url}`);
|
|
const data = await res.json();
|
|
const models = (data.models ?? []).map((m) => m.name);
|
|
return { ok: true, models };
|
|
}
|
|
|
|
async chat({ model, messages, tools, temperature = 0, numCtx = 8192, timeoutMs }) {
|
|
const body = {
|
|
model,
|
|
messages,
|
|
stream: false,
|
|
options: { temperature },
|
|
};
|
|
if (numCtx) body.options.num_ctx = numCtx;
|
|
if (tools && tools.length) body.tools = tools;
|
|
|
|
const res = await fetch(`${this.url}/api/chat`, {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify(body),
|
|
signal: AbortSignal.timeout(timeoutMs ?? this.timeoutMs),
|
|
});
|
|
if (!res.ok) {
|
|
const t = await res.text();
|
|
throw new Error(`Ollama chat HTTP ${res.status}: ${t.slice(0, 300)}`);
|
|
}
|
|
const data = await res.json();
|
|
const message = data.message ?? {};
|
|
return {
|
|
role: message.role ?? "assistant",
|
|
content: message.content ?? "",
|
|
toolCalls: message.tool_calls ?? [],
|
|
promptEvalCount: data.prompt_eval_count ?? 0,
|
|
evalCount: data.eval_count ?? 0,
|
|
raw: data,
|
|
};
|
|
}
|
|
}
|
|
|
|
export async function listModels() {
|
|
const o = new Ollama();
|
|
const res = await fetch(`${o.url}/api/tags`);
|
|
if (!res.ok) throw new Error(`Ollama not reachable (HTTP ${res.status})`);
|
|
const data = await res.json();
|
|
return (data.models ?? []).map((m) => m.name);
|
|
}
|