# Warning: Using cached embedding from version 1.0.0, but current model is version 2.0.0. Embedding may be stale.

- **ID:** `llm/llm-caching-stale-embedding`
- **Domain:** llm
- **Category:** runtime_error
- **Verification:** ai_generated
- **Fix Rate:** 85%

## Root Cause

Embedding cache from a previous model version is reused after model update, causing dimension or semantic drift.

## Version Compatibility

| Version | Status | Introduced | Deprecated |
|---------|--------|------------|------------|
| langchain 0.1.10 | active | — | — |
| langchain 0.1.11 | active | — | — |
| chromadb 0.4.22 | active | — | — |

## Workarounds

1. **Clear embedding cache and re-index: chroma_collection.delete(where={}); then re-embed all documents with new model version** (95% success)
   ```
   Clear embedding cache and re-index: chroma_collection.delete(where={}); then re-embed all documents with new model version
   ```
2. **Pin embedding model version in config: EMBEDDING_MODEL = 'text-embedding-3-small@v1' (if version pinning is supported)** (80% success)
   ```
   Pin embedding model version in config: EMBEDDING_MODEL = 'text-embedding-3-small@v1' (if version pinning is supported)
   ```

## Dead Ends

- **Ignoring warning and continuing to use cache** — Stale embeddings cause retrieval failures or inaccurate results, leading to silent data issues. (95% fail)
- **Disabling caching entirely** — Increases latency and API costs without solving root cause of version mismatch. (70% fail)