Unverified50% confidenceFactExact time
VaultLedger uses the qwen2.5:7b model running locally via Ollama, extracts PDF text with PyMuPDF, constrains output with Pydantic schema, performs comparison with pandas, and uses Streamlit as the interface.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedLocal Receipt Sorter's tech stack includes PyMuPDF for parsing PDFs, Streamlit for providing the interactive interface, and pandas for handling exports.70% similarUnverifiedVaultRAG's document ingestion flow is: the user uploads a PDF in the React interface, FastAPI receives the file, LangChain splits text chunks using RecursiveCharacterTextSplitter, then embedding vectors are generated via Ollama and stored in the local vector store.63% similarUnverifiedllama.cpp supports quantized models in GGUF format and includes a built-in Web UI page.62% similarUnverifiedOllama 通过 Modelfile 中的 TEMPLATE 字段管理 chat template 配置，模型发布者也会在 GGUF 文件元数据中嵌入推荐模板59% similarUnverifiedGeopandas is a core library in the Python ecosystem for geospatial data processing; it extends pandas' DataFrame structure to support geometric objects (such as points, lines and polygons).57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058361API
curl https://kongchang.com/api/v1/knowledge/claims/1058361MCP
get_claim(id=1058361)