claude-self-reflect 2.3.4 → 2.3.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -4
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -145,13 +145,11 @@ If you must know:
|
|
|
145
145
|
- **Vector DB**: Qdrant (local, your data stays yours)
|
|
146
146
|
- **Embeddings**:
|
|
147
147
|
- Local (Default): FastEmbed with sentence-transformers/all-MiniLM-L6-v2
|
|
148
|
-
- Cloud (Optional): Voyage AI (200M free tokens/month)
|
|
148
|
+
- Cloud (Optional): Voyage AI (200M free tokens/month)
|
|
149
149
|
- **MCP Server**: Python + FastMCP
|
|
150
150
|
- **Search**: Semantic similarity with time decay
|
|
151
151
|
|
|
152
|
-
|
|
153
|
-
|
|
154
|
-
**Note**: Local mode uses FastEmbed, the same efficient embedding library used by the Qdrant MCP server, ensuring fast and private semantic search without external dependencies.
|
|
152
|
+
Both embedding options work well. Local mode uses FastEmbed for privacy and offline use. Cloud mode uses Voyage AI for enhanced accuracy when internet is available. We are not affiliated with Voyage AI.
|
|
155
153
|
|
|
156
154
|
### Want More Details?
|
|
157
155
|
|