Add recemment modifié page accueil
This commit is contained in:
31
notes/research/design/ai/semantic-search.md
Normal file
31
notes/research/design/ai/semantic-search.md
Normal file
@ -0,0 +1,31 @@
|
||||
---
|
||||
title: "Semantic Search Research"
|
||||
date: "10-11-2025"
|
||||
last_modified: "10-11-2025:19:21"
|
||||
tags: ["research", "ai", "search"]
|
||||
---
|
||||
|
||||
# Semantic Search
|
||||
|
||||
## Current Search
|
||||
|
||||
Keyword-based with scoring.
|
||||
|
||||
## Semantic Search
|
||||
|
||||
Use embeddings for similarity:
|
||||
- OpenAI embeddings API
|
||||
- Local models (sentence-transformers)
|
||||
- Vector database (Pinecone, Weaviate)
|
||||
|
||||
## Implementation
|
||||
|
||||
1. Generate embeddings for all notes
|
||||
2. Store in vector DB
|
||||
3. Query with user search
|
||||
4. Return top-k similar
|
||||
|
||||
## Cost Analysis
|
||||
|
||||
OpenAI: /tmp/generate_notes.sh.0001 per 1K tokens
|
||||
Local: Free but slower
|
||||
Reference in New Issue
Block a user