Issues
- 6
- 0
Add Support for Cached Tokens in OpenAI Usage Model
#1506 opened by KamilKaletka - 1
bug: NPE when processing ByteArrayResource
#1571 opened by ogbozoyan - 0
In Anthropic 3 API, Response body is not showing in stacktrace if ChatModel.stream() fails
#1583 opened by jombidev - 2
com.google.api.gax.rpc.UnknownException: java.net.SocketTimeoutException: Read timed out
#1577 opened by account123456789 - 0
- 1
dislodge google vertex embedding model from chat model
#1579 opened by joshlong - 2
- 0
Internalization of resources
#1578 opened by marcingrzejszczak - 0
BiFunction with ToolContext Fails Due to Incorrect Type Resolution in Spring Cloud Function
#1576 opened by sfcodes - 0
Fix docs link for OpenAI in Spring AI
#1574 opened by devholic22 - 0
向量库返回的 Document 中 的 distance 字段应统一
#1568 opened by yyqqing - 0
Spring have to always create collection ChromaDB
#1567 opened by novakma2 - 0
performance regression (?) when compiling a Spring Boot application with GraalVM
#1565 opened by joshlong - 0
Support multimodality in chat completion output
#1563 opened by ThomasVitale - 0
Review the Media APIs for multimodality
#1562 opened by ThomasVitale - 1
OpenAI: Support audio modality in chat completion
#1560 opened by ThomasVitale - 6
How to change the runtime model defaultOptions of ollama here , see getContextChatClient method
#1460 opened by zjarlin - 2
Inaccurate warning for VertexAI Gemini Function Calling
#1543 opened by ddobrin - 0
- 1
ChromaApi have a bug: when metadata param equal hnsw:M and value equal 1024 ,chroma's rest api is success ,but spring-ai-chroma-store is error
#1548 opened by CodingNowPls - 0
Why are AnthropicChatOptions's getModel(), getFrequencyPenalty(), and getPresencePenalty() methods not implemented?
#1546 opened by cowboysj - 0
docs: Fix Typos in Documentation
#1544 opened by cowboysj - 0
Add amazon document db as a vector store
#1541 opened by tstephen1 - 0
Investigate depdency on Boot in a few projects
#1540 opened by markpollack - 1
Why is dashscope not supported?
#1539 opened by chenm1xuexi - 2
Documentation: Correct response key from "generation" to "completion" in example code
#1533 opened by LuizyHub - 8
Reopening bug in M3 - ChatResponse Metadata is overwritten by advisors
#1537 opened by chetan-galgali - 0
Add Ollama embedding usage metadata
#1536 opened by tzolov - 1
- 0
Potential Issue with 1.0.0-M3 and 1.0.0-SNAPSHOT Documentation URLs and Outdated API Docs
#1523 opened by ullenboom - 0
Unsupported or unrecognized SSL message
#1530 opened by GP-GUO - 0
- 0
Using models via OpenRouter returns an error.
#1522 opened by ErykCh - 0
- 0
When the function call is used together with RAG, the function call does not work.
#1515 opened by oasis-zhou - 0
Add a new test case for AnthropicAutoConfigurationIT. Considering call(null).
#1517 opened by jonatasemidio - 0
- 0
Add support for Voyage embedding model
#1513 opened by kevintsai1202 - 2
The document segmentation vectorization failed.
#1499 opened by oasis-zhou - 2
Common types for text-to-speech
#1496 opened by habuma - 1
Adding support for OpenAI's real-time model
#1464 opened by kevintsai1202 - 3
Failed to create collection on ChromaVectorStore
#1457 opened by NineWoranop - 1
The ElasticsearchVectorStoreAutoConfiguration is not public as all the others
#1462 opened by jcgouveia - 0
- 0
The document segmentation vectorization failed.
#1498 opened by oasis-zhou - 1
Tika Document Reader issue (OpenAI and Mistral)
#1476 opened by kursatufukcoskun - 0
Simply implementation of Usage in OpenAI support
#1487 opened by markpollack - 3
NullPointerException with Ollama + streaming + image
#1459 opened by habuma - 2
Introduce TranscriptionModel interface
#1478 opened by habuma