mirror of
https://github.com/Crosstalk-Solutions/project-nomad.git
synced 2026-05-25 13:55:05 +02:00
b194dfa136
Some Ollama installs ship nomic-embed-text:v1.5 with the embedding model's default num_ctx=2048, which the RAG chunker (sized for ~1500 tokens of estimated content with ratio=2 chars/token) can exceed on dense PDFs. The result is `400 the input length exceeds the context length` from /api/embed, which then hits the OpenAI-compatible fallback (which also errors), and surfaces as a BadRequestError. Pass options.num_ctx=8192 (nomic-embed-text v1.5's RoPE-extrapolated max) and truncate=true (silent truncation safety net) on every embed call so we don't depend on the local modelfile defaults. Reported on #756 by @NC4WD; same root cause as #369 and #670 which were closed without an actual fix. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| app | ||
| bin | ||
| commands | ||
| config | ||
| constants | ||
| database | ||
| docs | ||
| inertia | ||
| providers | ||
| public | ||
| resources/views | ||
| start | ||
| tests | ||
| types | ||
| util | ||
| views | ||
| .editorconfig | ||
| .env.example | ||
| ace.js | ||
| adonisrc.ts | ||
| eslint.config.js | ||
| package-lock.json | ||
| package.json | ||
| tailwind.config.ts | ||
| tsconfig.json | ||
| vite.config.ts | ||