French institutional portfolio analytics with RAG and local LLM
Project description
quarq
French institutional portfolio analytics with RAG and local LLM.
pip install quarq
What it is
quarq is a CLI tool for institutional portfolio analysis. It combines a live data pipeline (French equities, ECB macro, FRED rates) with a RAG engine over financial documents (SFDR filings, ECB FSR, fund prospectuses) and a local LLM for plain-English narrative generation.
Your portfolio data never leaves your machine.
Status
Work in progress. v0.1.0 coming soon.
Stack
- Data: yfinance, FRED, ECB SDW, OECD (direct REST, no framework dependency)
- RAG: sentence-transformers + ChromaDB (local, persistent)
- LLM: Qwen3 / Mistral via LM Studio (local inference)
- Report: Plotly 6 + Jinja2, PDF via playwright
- CLI: textual + rich
Usage (coming in v0.1.0)
quarq status quarq report --portfolio ./portfolio.toml --format pdf quarq query "What does the ECB FSR say about CAC 40 concentration?" quarq rag add ./docs/
Author
zkmarc — https://github.com/yodablocks
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file quarq-0.0.3.tar.gz.
File metadata
- Download URL: quarq-0.0.3.tar.gz
- Upload date:
- Size: 1.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1d097018e41bad450bbf85f6100a8d879831438dd7d0a383bd2f4d33e07bf962
|
|
| MD5 |
af176286dede91e90ecb38667df69ee8
|
|
| BLAKE2b-256 |
337bed6d6ad4d5c430559f70cceb908845dd2ffd4650a1b633d79f9c8fa5acf0
|
File details
Details for the file quarq-0.0.3-py3-none-any.whl.
File metadata
- Download URL: quarq-0.0.3-py3-none-any.whl
- Upload date:
- Size: 2.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
00262750447fb0ceea988d390580607299e66c1bdd01ee79c93400bea48b04c0
|
|
| MD5 |
b71af17a94e39eb1bb63070f77c038c9
|
|
| BLAKE2b-256 |
bb50b3971b808a56f2ee4c2e13343be2e769b311735b9e330ed11526431f7bfd
|