Hey everyone, I am using hybrid search. The embed...
# community-help
a
Hey everyone, I am using hybrid search. The embedding is being used through OpenAI as provider. While searching, it says
Copy code
RequestMalformed: Request failed with HTTP code 400 | Server said: Prefix search is not supported for remote embedders. Please set `prefix=false` as an additional search parameter to disable prefix searching
Setting
prefix=false
did work. But we are loosing some basic semantic search. eg. Keyword
Apple
doesn't work where the content has this kind of matching
... Apple's ...
. So, it's missing documents where it has and single quote. But, without the vector search it works. Asking for suggestions and help on how can we take the best of Hybrid search. Thanks 🙏
f
Are you using Typesense cloud or self-hosting?
a
Cloud
But, the development mode is in the Docker version
f
Could you share your cluster's ID and a sample curl request that replicates the behavior?
Is the issue present on production?
a
We haven't shipped this to production yet.
Our production app uses Typesense cloud, and for local development we are using Docker image. Should we test this one with and cloud cluster while developing?
f
Could you provide a set of the data that replicates the behavior similar to this? https://gist.github.com/jasonbosco/7c3432713216c378472f13e72246f46b/
👀 1
We'd generally advise you use Typesense cloud both on production and while developing, but having the same Typesense version on Docker will be the same as well. The main thing to watch out for is not to have different versions / architecture on production and development
💡 1
a
Makes sense, will get back with the gist 🙌
❤️ 1
Note: our both environments (Cloud & Docker) are in version
29.0
Another point I missed, the entire error was:
Copy code
RequestMalformed: Request failed with HTTP code 400 | Server said: Prefix search is not supported for remote embedders. Please set `prefix=false` as an additional search parameter to disable prefix searching