Unverified50% confidenceFactExact time
Local Receipt Sorter uses the Gemma 3 vision model (4B parameters) served locally through Ollama, and the model can be switched to the 12B version via an environment variable to improve accuracy.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
Unverified语义向量匹配借助FAISS等向量检索库将用户输入映射为高维向量后进行最近邻搜索55% similarUnverifiedTesseract can be forced into LSTM mode via the --oem 1 parameter, combined with the --psm parameter to select the page segmentation mode, and the tessdata_best repository provides high-accuracy models54% similarUnverifiedn8n displays data in three ways: Schema, Table, and JSON, which are three different views of the same data.53% similarUnverifiedThis solution uses the locally deployed Qwen3 large model at the question classifier node.51% similarUnverifiedThe 0.6B-scale model is suitable for fast request classification in edge or high-concurrency scenarios.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024287API
curl https://kongchang.com/api/v1/knowledge/claims/1024287MCP
get_claim(id=1024287)