#community-help

Using Multilingual-e5-Base Model in Huggingface

TLDR Bill asked about using the Multilingual-e5-Base model and the required structure. Kishore Nallan advised that prefixes are handled automatically in Typesense. The user had error issues but resolved them, and Kishore Nallan mentioned a recent fix.

Join the chat

Sep 06, 2023 (3 weeks ago)

Photo of md5-be53735a2b0297bb542711c1d2ecea45

Bill

01:15 PM

Hi, the multilingual-e5-base that you added in huggingface is better/faster than the paraphrase-multilingual-mpnet-base-v2 model?

Photo of md5-4e872368b2b2668460205b409e95c2ea

Kishore Nallan

01:17 PM

Yes, generally the e5 family is close to state of the art since they are more recent.

Bill

01:18 PM

Okay, what's the structure in order to use it in the collection? Do I have to add "query:"?

01:19

Bill

01:19 PM

"model_config": {
"model_name": "ts/multilingual-e5-base",
"indexing_prefix": "query:",
"query_prefix": "query:"
}

01:20

Bill

01:20 PM

or "passage:" ?

Kishore Nallan

01:26 PM

Yes the same format as all other e5 models that follow that convention.

Bill

01:27 PM

Should I use passage or query?

Kishore Nallan

01:34 PM

In typesense this is already handled for you. You don't have to prefix anything.

Bill

01:35 PM

Ok, so the filed structure will be:
{
"name": "embedding",
"type": "float[]",
"embed": {
"from": ["product_name"],
"model_config": {
"model_name": "ts/multilingual-e5-base",
"indexing_prefix": "passage:",
"query_prefix": "query:"
}
}
}
Am i right?

Kishore Nallan

01:37 PM

You can leave out those prefix fields. They should default automatically.

Bill

01:38 PM

So only the model_name should I add?

Kishore Nallan

04:17 PM

Yes

Sep 07, 2023 (2 weeks ago)

Bill

01:32 PM

I'm trying to create the following collection but I get error:
{
"name": "products",
"fields": [
{
"name": "brand",
"type": "string"
},
{
"name": "embedding",
"type": "float[]",
"embed": {
"from": [
"brand"
],
"model_config": {
"model_name": "ts/multilingual-e5-base"
}
}
}
]
}

01:32

Bill

01:32 PM

{
"message": "Bad request."
}

01:32

Bill

01:32 PM

In localhost, macOS with docker compose

01:33

Bill

01:33 PM

In logs I get this -> E20230907 13:33:24.950084 195 batched_indexer.cpp:229] Raw error: [json.exception.parse_error.101] parse error at line 1, column 1: syntax error while parsing value - unexpected end of input; expected '[', '{', or a literal

Photo of md5-8813087cccc512313602b6d9f9ece19f

Jason

03:13 PM

Could you try replicating it with curl? If you can replicate it, could you share the full curl command?

Sep 08, 2023 (2 weeks ago)

Bill

06:18 AM

Problem solved. It was an issue with the model

Kishore Nallan

06:19 AM

We actually fixed this in recent 0.25.1 RC build.

Typesense

Lightning-fast, open source search engine for everyone | Knowledge Base powered by Struct.AI

Indexed 2764 threads (79% resolved)

Join Our Community Manage subscription

Similar Threads

Converting finbert to ONNX for Typesense Model Repository

Walter requested the conversion of finbert to onnx from Jason. Conversation included discussions about model differences and technical adjustments, ultimately ending in a successful conversion and a plan to handle a known bug.

Issue with Embedding Error in Version 0.25.0.rc63

Bill reported a bug in version 0.25.0.rc63 regarding a problem with updating or emplacing a document and receiving an embedding error. This was resolved in version 0.25.0.rc65, but further discussion ensued regarding the function of 'index' in the update feature.

1mo

Issues with Semantic Search in OpenAI Embeddings

Semyon was having issues while creating a schema for semantic search with OpenAI embeddings. Jason gave multiple suggestions for troubleshooting but none of them worked. The error was narrowed down to possibly being related to Semyon's specific OpenAI account or the OpenAI API key. The thread ended with Jason suggesting Semyon to check billing and make a direct API call to OpenAI.

Resolving Issues While Upgrading Typesense Server

Ayush had queries about upgrading their Typesense server and updating collections using auto-embeddings. Kishore Nallan clarified all issues, but later discovered that reindexing of non auto-embedded vector fields only is currently supported during altering.

Discussing Firestore Extension and Collection Schema in Typesense

Loic asks about settings in Firestore Extension and experiences issues with the collection schema in Typesense. Discussion with Jason is ongoing.