Add recemment modifié page accueil

notes/research/design/ai/auto-tagging.md

@@ -0,0 +1,38 @@
+---
+title: Automatic Tagging
+date: 10-11-2025
+last_modified: 11-11-2025:17:56
+tags:
+    - research
+    - ai
+    - nlp
+---
+
+# Automatic Tagging
+
+## Goal
+
+Suggest tags based on note content.
+
+## Approaches
+
+### Rule-based
+- Keyword extraction
+- TF-IDF
+
+### ML-based
+- Zero-shot classification
+- Fine-tuned model
+
+### Hybrid
+- Combine both approaches
+
+
+## Training Data
+
+Use existing notes with tags as 
+training set.
+
+
+
+[texte](url)

notes/research/design/ai/semantic-search.md

@@ -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