- 218d001: feat (provider): Add maxImagesPerCall setting to all image providers.
- fe816e4: fix (provider/openai): streamObject with o1
- ba62cf2: feat (provider/openai): automatically map maxTokens to max_completion_tokens for reasoning models
- 3c3fae8: fix (provider/openai): add o1-mini-2024-09-12 and o1-preview-2024-09-12 configurations
- Updated dependencies [90fb95a]
- Updated dependencies [e6dfef4]
- Updated dependencies [6636db6]
- @ai-sdk/[email protected]
- f8c6acb: feat (provider/openai): automatically simulate streaming for reasoning models
- d0041f7: feat (provider/openai): improved system message support for reasoning models
- 4d2f97b: feat (provider/openai): improve automatic setting removal for reasoning models
- 19a2ce7: feat (ai/core): add aspectRatio and seed options to generateImage
- 6337688: feat: change image generation errors to warnings
- Updated dependencies [19a2ce7]
- Updated dependencies [19a2ce7]
- Updated dependencies [6337688]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- b19aa82: feat (provider/openai): add predicted outputs token usage
- a4241ff: feat (provider/openai): add o3 reasoning model support
- 5ed5e45: chore (config): Use ts-library.json tsconfig for no-UI libs.
- Updated dependencies [5ed5e45]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- d4fad4e: fix (provider/openai): fix reasoning model detection
- 3fab0fb: feat (provider/openai): support reasoning_effort setting
- e956eed: feat (provider/openai): update model list and add o1
- 6faab13: feat (provider/openai): simulated streaming setting
- 09a9cab: feat (ai/core): add experimental generateImage function
- Updated dependencies [09a9cab]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [0984f0b]
- @ai-sdk/[email protected]
- a9a19cb: fix (provider/openai,groq): prevent sending duplicate tool calls
- fc18132: feat (ai/core): experimental output for generateText
- Updated dependencies [b446ae5]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- b748dfb: feat (providers): update model lists
- Updated dependencies [c3ab5de]
- @ai-sdk/[email protected]
- 5e6419a: feat (provider/openai): support streaming for reasoning models
- 66060f7: chore (release): bump major version to 4.0
- 79644e9: chore (provider/openai): remove OpenAI facade
- 0d3d3f5: chore (providers): remove baseUrl option
- Updated dependencies [b469a7e]
- Updated dependencies [dce4158]
- Updated dependencies [c0ddc24]
- Updated dependencies [b1da952]
- Updated dependencies [dce4158]
- Updated dependencies [8426f55]
- Updated dependencies [db46ce5]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [8426f55]
- @ai-sdk/[email protected]
- Updated dependencies [dce4158]
- Updated dependencies [dce4158]
- @ai-sdk/[email protected]
- 79644e9: chore (provider/openai): remove OpenAI facade
- 0d3d3f5: chore (providers): remove baseUrl option
- Updated dependencies [b1da952]
- @ai-sdk/[email protected]
- 66060f7: chore (release): bump major version to 4.0
- Updated dependencies [b469a7e]
- Updated dependencies [c0ddc24]
- Updated dependencies [db46ce5]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 0bc4115: feat (provider/openai): support predicted outputs
- 54a3a59: fix (provider/openai): support object-json mode without schema
- 3b1b69a: feat: provider-defined tools
- Updated dependencies [aa98cdb]
- Updated dependencies [1486128]
- Updated dependencies [7b937c5]
- Updated dependencies [3b1b69a]
- Updated dependencies [811a317]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- b9b0d7b: feat (ai): access raw request body
- Updated dependencies [b9b0d7b]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 741ca51: feat (provider/openai): support mp3 and wav audio inputs
- 39fccee: feat (provider/openai): provider name can be changed for 3rd party openai compatible providers
- 3f29c10: feat (provider/openai): support metadata field for distillation
- e8aed44: Add OpenAI cached prompt tokens to experimental_providerMetadata for generateText and streamText
- 5aa576d: feat (provider/openai): support store parameter for distillation
- Updated dependencies [d595d0d]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 7efa867: feat (provider/openai): simulated streaming for reasoning models
- 8132a60: feat (provider/openai): support reasoning token usage and max_completion_tokens
- Updated dependencies [273f696]
- @ai-sdk/[email protected]
- a0991ec: feat (provider/openai): add o1-preview and o1-mini models
- e0c36bd: feat (provider/openai): support image detail
- d1aaeae: feat (provider/openai): support ai sdk image download
- 03313cd: feat (ai): expose response id, response model, response timestamp in telemetry and api
- Updated dependencies [03313cd]
- Updated dependencies [3be7c1c]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 28cbf2e: fix (provider/openai): support tool call deltas when arguments are sent in the first chunk
- 26515cb: feat (ai/provider): introduce ProviderV1 specification
- Updated dependencies [26515cb]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [09f895f]
- @ai-sdk/[email protected]
- d5b6a15: feat (provider/openai): support partial usage information
- Updated dependencies [d67fa9c]
- @ai-sdk/[email protected]
- Updated dependencies [f2c025e]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- f42d9bd: fix (provider/openai): support OpenRouter streaming errors
- Updated dependencies [6ac355e]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 4ffbaee: fix (provider/openai): fix strict flag for structured outputs with tools
- dd712ac: fix: use FetchFunction type to prevent self-reference
- Updated dependencies [dd712ac]
- @ai-sdk/[email protected]
- 89b18ca: fix (ai/provider): send finish reason 'unknown' by default
- Updated dependencies [dd4a0f5]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [4bd27a9]
- Updated dependencies [845754b]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 029af4c: feat (ai/core): support schema name & description in generateObject & streamObject
- Updated dependencies [029af4c]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- d58517b: feat (ai/openai): structured outputs
- c0a73ee: feat (provider/openai): add gpt-4o-2024-08-06 to list of supported models
- Updated dependencies [d58517b]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [96aed25]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 7a2eb27: feat (provider/openai): make role nullish to enhance provider support
- Updated dependencies [9614584]
- Updated dependencies [0762a22]
- @ai-sdk/[email protected]
- Updated dependencies [a8d1c9e9]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [4f88248f]
- @ai-sdk/[email protected]
- 2b9da0f0: feat (core): support stopSequences setting.
- 909b9d27: feat (ai/openai): Support legacy function calls
- a5b58845: feat (core): support topK setting
- 4aa8deb3: feat (provider): support responseFormat setting in provider api
- 13b27ec6: chore (ai/core): remove grammar mode
- Updated dependencies [2b9da0f0]
- Updated dependencies [a5b58845]
- Updated dependencies [4aa8deb3]
- Updated dependencies [13b27ec6]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 89947fc5: chore (provider/openai): update model list for type-ahead support
- b7290943: feat (ai/core): add token usage to embed and embedMany
- Updated dependencies [b7290943]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [d481729f]
- @ai-sdk/[email protected]
- 5edc6110: feat (ai/core): add custom request header support
- Updated dependencies [5edc6110]
- Updated dependencies [5edc6110]
- Updated dependencies [5edc6110]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [02f6a088]
- @ai-sdk/[email protected]
- 1b37b8b9: fix (@ai-sdk/openai): only send logprobs settings when logprobs are requested
- eba071dd: feat (@ai-sdk/azure): add azure openai completion support
- 1ea890fe: feat (@ai-sdk/azure): add azure openai completion support
- Updated dependencies [85712895]
- Updated dependencies [85712895]
- @ai-sdk/[email protected]
- 4728c37f: feat (core): add text embedding model support to provider registry
- 7910ae84: feat (providers): support custom fetch implementations
- Updated dependencies [7910ae84]
- @ai-sdk/[email protected]
- f9db8fd6: feat (@ai-sdk/openai): add parallelToolCalls setting
- fc9552ec: fix (@ai-sdk/azure): allow for nullish delta
- 7530f861: fix (@ai-sdk/openai): add internal dist to bundle
- 8b1362a7: chore (@ai-sdk/openai): expose models under /internal for reuse in other providers
- 0e78960c: fix (@ai-sdk/openai): make function name and arguments nullish
- a68fe74a: fix (@ai-sdk/openai): allow null tool_calls value.
- Updated dependencies [102ca22f]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- fca7d026: feat (provider/openai): support streaming tool calls that are sent in one chunk
- Updated dependencies [09295e2e]
- Updated dependencies [09295e2e]
- Updated dependencies [043a5de2]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- a1d08f3e: fix (provider/openai): handle error chunks when streaming
- beb8b739: fix (provider/openai): return unknown finish reasons as unknown
- fb42e760: feat (provider/openai): send user message content as text when possible
- f39c0dd2: feat (provider): implement toolChoice support
- Updated dependencies [f39c0dd2]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 2b18fa11: fix (provider/openai): remove object type validation
- 24683b72: fix (providers): Zod is required dependency
- Updated dependencies [8e780288]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [6a50ac4]
- Updated dependencies [6a50ac4]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- 4e3c922: fix (provider/openai): introduce compatibility mode in which "stream_options" are not sent
- 6f48839: feat (provider/openai): add gpt-4o to the list of supported models
- 1009594: feat (provider/openai): set stream_options/include_usage to true when streaming
- 0f6bc4e: feat (ai/core): add embed function
- Updated dependencies [0f6bc4e]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [325ca55]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [276f22b]
- @ai-sdk/[email protected]
- Updated dependencies [41d5736]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- Updated dependencies [56ef84a]
- @ai-sdk/[email protected]
- 0833e19: Allow optional content to support Fireworks function calling.
- d6431ae: ai/core: add logprobs support (thanks @SamStenner for the contribution)
- 25f3350: ai/core: add support for getting raw response headers.
- Updated dependencies [d6431ae]
- Updated dependencies [25f3350]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- eb150a6: ai/core: remove scaling of setting values (breaking change). If you were using the temperature, frequency penalty, or presence penalty settings, you need to update the providers and adjust the setting values.
- Updated dependencies [eb150a6]
- @ai-sdk/[email protected]
- @ai-sdk/[email protected]
- c6fc35b: Add custom header and OpenAI project support.
- ab60b18: Simplified model construction by directly calling provider functions. Add create... functions to create provider instances.
- 2bff460: Fix build for release.
- 7b8791d: Support streams with 'chat.completion' objects.
- 7b8791d: Rename baseUrl to baseURL. Automatically remove trailing slashes.
- Updated dependencies [7b8791d]
- @ai-sdk/[email protected]