drjones/nexus-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

route local LLM to qwen3.8 on .128 (was gemma4:26b); think:false + num_ctx 8192

Browse Source
This commit is contained in:
drjones
2026-08-25 06:52:42 +00:00
parent d04fe5a3ca
commit 42a9f214f5
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/server/llmClient.ts
View File

@@ -1,7 +1,7 @@
// Shared local-LLM client — Ollama on shadow-death (.128). // Shared local-LLM client — Ollama on shadow-death (.128).
// Single source of truth for host/model across the whole app. // Single source of truth for host/model across the whole app.
export const OLLAMA_HOST = process.env.OLLAMA_HOST || 'http://10.30.20.128:11434'; export const OLLAMA_HOST = process.env.OLLAMA_HOST || 'http://10.30.20.128:11434';
export const OLLAMA_MODEL = process.env.OLLAMA_MODEL || 'gemma4:26b'; export const OLLAMA_MODEL = process.env.OLLAMA_MODEL || 'qwen3.8:latest';
export interface LocalModelOptions { export interface LocalModelOptions {
formatJson?: boolean; formatJson?: boolean;
@@ -18,6 +18,8 @@ export async function callLocalModel(prompt: string, opts: LocalModelOptions = {
options: { options: {
num_predict: opts.numPredict ?? 4096, num_predict: opts.numPredict ?? 4096,
temperature: opts.temperature ?? 0.2, temperature: opts.temperature ?? 0.2,
think: false,
num_ctx: 8192,
}, },
}; };
if (opts.formatJson) body.format = 'json'; if (opts.formatJson) body.format = 'json';