chris/write
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix AI prompt URL: use /ollama/v1/chat/completions for Open WebUI

Browse Source 
The server at ai.binarygnome.com is Open WebUI, not a bare Ollama
instance. Open WebUI proxies Ollama at /ollama/v1/... rather than /v1/...

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
chris 2026-05-24 20:35:11 -04:00
parent 6f12efd3fb
commit c5b7d7f774
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/routes/prompts.js
View File

@ -176,7 +176,7 @@ function nextFallback() {
// ── Shared AI call — uses the OpenAI-compatible chat completions API ───── // ── Shared AI call — uses the OpenAI-compatible chat completions API ─────
async function callOllama() { async function callOllama() {
const url = `${OLLAMA_URL}/v1/chat/completions` const url = `${OLLAMA_URL}/ollama/v1/chat/completions`
console.log(`[prompts] calling AI url=${url} model=${OLLAMA_MODEL}`) console.log(`[prompts] calling AI url=${url} model=${OLLAMA_MODEL}`)
const headers = { 'Content-Type': 'application/json' } const headers = { 'Content-Type': 'application/json' }
@ -212,7 +212,7 @@ const router = Router()
// Debug endpoint — no auth needed, only exposes connection status // Debug endpoint — no auth needed, only exposes connection status
router.get('/test', async (req, res) => { router.get('/test', async (req, res) => {
const result = { url: `${OLLAMA_URL}/api/generate`, model: OLLAMA_MODEL } const result = { url: `${OLLAMA_URL}/ollama/v1/chat/completions`, model: OLLAMA_MODEL }
try { try {
result.prompt = await callOllama() result.prompt = await callOllama()
result.status = 'ok' result.status = 'ok'