spring-projects / spring-projects/spring-ai

Embedding generation fails in 1.1.0, worked in 1.0.3

Open
#4,910 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 7h
Merged PRs (30d)
6

Description

@sunyuhan1998 Thank you for the PR! Rebased, squashed and merged as 9e43b7e10

Originally posted by @ilayaperumalg in https://github.com/spring-projects/spring-ai/issues/3804#issuecomment-3259018148

Embedding generation (using Ollama / bge-m3) works in Spring AI 1.0.3 but fails in 1.1.0 with the error below:

Caused by: com.fasterxml.jackson.databind.exc.MismatchedInputException: Trailing token (of type FIELD_NAME) found after value (bound as float[]): not allowed as per DeserializationFeature.FAIL_ON_TRAILING_TOKENS
at [Source: REDACTED (StreamReadFeature.INCLUDE_SOURCE_IN_LOCATION disabled); line: 1, column: 12870] (through reference chain: org.springframework.ai.openai.api.OpenAiApi$EmbeddingList["data"]->java.util.ArrayList[0]->org.springframework.ai.openai.api.OpenAiApi$Embedding["embedding"])
at com.fasterxml.jackson.databind.exc.MismatchedInputException.from(MismatchedInputException.java:63)
at com.fasterxml.jackson.databind.DeserializationContext.reportTrailingTokens(DeserializationContext.java:1840)
at com.fasterxml.jackson.databind.ObjectMapper._verifyNoTrailingTokens(ObjectMapper.java:5013)
at com.fasterxml.jackson.databind.ObjectMapper._readValue(ObjectMapper.java:4886)
at com.fasterxml.jackson.databind.ObjectMapper.readValue(ObjectMapper.java:3035)
at com.fasterxml.jackson.core.JsonParser.readValueAs(JsonParser.java:2458)
at org.springframework.ai.openai.api.OpenAiEmbeddingDeserializer.deserialize(OpenAiEmbeddingDeserializer.java:50)
at org.springframework.ai.openai.api.OpenAiEmbeddingDeserializer.deserialize(OpenAiEmbeddingDeserializer.java:43)
at com.fasterxml.jackson.databind.deser.SettableBeanProperty.deserialize(SettableBeanProperty.java:545)
at com.fasterxml.jackson.databind.deser.BeanDeserializer._deserializeWithErrorWrapping(BeanDeserializer.java:576)
at com.fasterxml.jackson.databind.deser.BeanDeserializer._deserializeUsingPropertyBased(BeanDeserializer.java:446)
at com.fasterxml.jackson.databind.deser.BeanDeserializerBase.deserializeFromObjectUsingNonDefault(BeanDeserializerBase.java:1493)
at com.fasterxml.jackson.databind.deser.BeanDeserializer.deserializeFromObject(BeanDeserializer.java:348)
at com.fasterxml.jackson.databind.deser.BeanDeserializer.deserialize(BeanDeserializer.java:185)
at com.fasterxml.jackson.databind.deser.std.CollectionDeserializer._deserializeFromArray(CollectionDeserializer.java:361)
at com.fasterxml.jackson.databind.deser.std.CollectionDeserializer.deserialize(CollectionDeserializer.java:246)
at com.fasterxml.jackson.databind.deser.std.CollectionDeserializer.deserialize(CollectionDeserializer.java:30)
at com.fasterxml.jackson.databind.deser.SettableBeanProperty.deserialize(SettableBeanProperty.java:545)
at com.fasterxml.jackson.databind.deser.BeanDeserializer._deserializeWithErrorWrapping(BeanDeserializer.java:576)
at com.fasterxml.jackson.databind.deser.BeanDeserializer._deserializeUsingPropertyBased(BeanDeserializer.java:446)
at com.fasterxml.jackson.databind.deser.BeanDeserializerBase.deserializeFromObjectUsingNonDefault(BeanDeserializerBase.java:1493)
at com.fasterxml.jackson.databind.deser.BeanDeserializer.deserializeFromObject(BeanDeserializer.java:348)
at com.fasterxml.jackson.databind.deser.BeanDeserializer.deserialize(BeanDeserializer.java:185)
at com.fasterxml.jackson.databind.deser.DefaultDeserializationContext.readRootValue(DefaultDeserializationContext.java:342)
at com.fasterxml.jackson.databind.ObjectReader._bindAndClose(ObjectReader.java:2125)
at com.fasterxml.jackson.databind.ObjectReader.readValue(ObjectReader.java:1501)
at org.springframework.http.converter.json.AbstractJackson2HttpMessageConverter.readJavaType(AbstractJackson2HttpMessageConverter.java:395)
... 27 common frames omitted

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with org.springframework.ai.openai.api.OpenAiEmbeddingDeserializer, especially line 50 in OpenAiEmbeddingDeserializer.java, and reproduce embedding generation with Ollama bge-m3 across Spring AI 1.0.3 and 1.1.0. Trace the response parsing that produces the trailing-token error; done means the 1.1.0 response deserializes successfully without regressing the earlier behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
java, ollama, spring-boot
Domain
ai, api, backend
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.