Catherine Renelle 401147009a Increase Ollama context window to 16k tokens ...

Ollama defaults to 2048 tokens which is far too small for page context
data + 15 tool definitions + conversation history. Added num_ctx=16384
via the options field on all Ollama requests. With Qwen at ~4GB and
7GB VRAM free this fits comfortably.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-12 19:25:24 -05:00

frontend

Run AI classification in background with SignalR notifications

2026-02-10 23:53:14 -05:00

src

Increase Ollama context window to 16k tokens

2026-02-12 19:25:24 -05:00

.dockerignore

Add .dockerignore files and increase Node memory limit

2026-02-08 09:53:47 -05:00

.env.example

Initial commit: Purrse personal finance app

2026-02-08 08:56:46 -05:00

.gitignore

Fix .gitignore excluding frontend plugins and test files

2026-02-08 10:04:19 -05:00

docker-compose.yml

Add Docker image cleanup container to compose stack

2026-02-10 19:07:53 -05:00

Purrse.sln

Implement Phase 6: automated bank sync (Plaid + SimpleFIN) & settings

2026-02-08 15:08:23 -05:00

S

Description

No description provided

MIT 1.5 MiB

Languages

C# 65%

Vue 30.2%

TypeScript 4.6%

Dockerfile 0.2%