RedisSemanticCache with LangChain not working after migrating from Redis to Dragonfly

Dragonfly Technical
1 

Hi everyone,

I’m running into an issue after migrating from Redis to Dragonfly and was wondering if anyone has experienced something similar.

I previously had a system working correctly using Redis together with LangChain’s RedisSemanticCache. Semantic caching worked as expected.

I’ve now migrated the backend to Dragonfly. The standard (non-semantic) cache works fine, with no errors and expected behavior. However, the semantic cache does not seem to work anymore:

No errors are thrown

The application runs normally

Cache entries appear to be written/read for the normal cache

But semantic cache hits never occur

From the application side everything looks correct, and the same code worked with Redis before the migration.

My questions are:

Is RedisSemanticCache fully compatible with Dragonfly?

Are there any known limitations regarding vector similarity / semantic caching features?

Is there any additional configuration required in Dragonfly for this use case?

Any pointers, documentation, or similar experiences would be greatly appreciated.
2

Hi @blancamartnez01,

Thank you for choosing Dragonfly, and sorry for the trouble you’re experiencing with RedisSemanticCache.

The issue is likely due to compatibility. Dragonfly has its own built-in search (Dragonfly Search), and its FT.SEARCH command does not yet support all the options that RediSearch does. This gap is probably why your semantic cache isn’t hitting.

We’d really like to investigate this. Could you please open a GitHub issue on our repo with your specific use case details and potentially error logs? This helps us track and prioritize these compatibility needs.