Faiss — Fast vector similarity search at billion scale
Faiss — Fast vector similarity search at billion scale
Start with meaning, then move to detail.
This lesson explains Faiss — Fast vector similarity search at billion scale as part of getting started with Hermes correctly. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect Skill metadata, Reference: full SKILL.md, When to use FAISS, then verify failure modes and version compatibility.
No prior experience is required; follow the steps on a safe test setup first.
A clear outcome before you read.
- Understand Faiss — Fast vector similarity search at billion scale without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Skill
- An instruction bundle that teaches Hermes a repeatable workflow without necessarily adding an external service.
Fast vector similarity search at billion scale
What does the source say, and in what order?
- 01Skill metadata
Start here to understand the core idea or structure.
- 02Reference: full SKILL.md
Read this after the foundation, then connect it to the previous step.
- 03When to use FAISS
Read this after the foundation, then connect it to the previous step.
- 04Quick start
Read this after the foundation, then connect it to the previous step.
- 05Installation
Read this after the foundation, then connect it to the previous step.
- 06Basic usage
Read this after the foundation, then connect it to the previous step.
- 07Index types
Read this after the foundation, then connect it to the previous step.
- 081. Flat (exact search)
Read this after the foundation, then connect it to the previous step.
- 092. IVF (inverted file) - Fast approximate
Read this after the foundation, then connect it to the previous step.
- 103. HNSW (Hierarchical NSW) - Best quality/speed
Finish here to verify the result and special cases.
Copy only after you understand the effect.
# CPU only
pip install faiss-cpu
# GPU support
pip install faiss-gpu## Index types
### 1. Flat (exact search)### 2. IVF (inverted file) - Fast approximateRead the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.