swiss_army_llama
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures
GraphCanon updated 2w · GitHub synced 2w
Decision brief
Swiss_army_llama offers a versatile semantic text search FastAPI service with precomputed embeddings, similarity measures, and support for various file types via textract.
Good fit when
- For projects requiring a comprehensive API solution that includes built-in support for diverse file formats like PDF, image, audio and more through textract
- When you need integration with the llama-cpp-python library for advanced text search capabilities
Avoid when
- Avoid if your project is strictly focused on real-time embeddings calculation without leveraging precomputed data
- Not suitable for developers looking to avoid extensive system dependencies listed in its requirements
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (526d since push)
- As of 2w
- Provenance
- Not a fork · Personal account
- As of 2w
- Security (OSV)
- No criticals
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install swiss_army_llamaSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
This Python-based repository offers a FastAPI service focused on semantic text search with support for various file types via textract, leveraging precomputed embeddings and advanced similarity techniques.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 8, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 8, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 8, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Requirements
System requirements for running the application (to support all the file types handled by textract):
sudo apt-get update
sudo apt-get install libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig -y
Python Requirements:
aioredis
aioredlock
aiosqlite
apscheduler
faiss-cpu
fast_vector_similarity
fastapi
faster-whisper
filelock
httpx
llama-cpp-python
magika
mutagen
nvgpu
pandas
pillow
psutil
pydantic
PyPDF2
pytest
python-decouple
python-multipart
pytz
redis
ruff
scikit-learn
scipy
sqlalchemy
textract-py3
uvicorn
uvloop
zstandard
License
This project is licensed under the MIT License.
For agents
This page has a .md twin and JSON over the API.