v1.3.0

1.3.0 (2024-06-26)

Features

• infer project ID when user don't specify and throw if inference fails (6b3e68e)

Bug Fixes

• improve error message to help with debugging (8a937d5)

v1.2.0

1.2.0 (2024-05-22)

Features

• allow users to pass string as system instruction (a824162)
• enable inference request to tuned model. (de9c4c2)
• infer location if user doesn't specifies it. (b8d4af1)
• support RAG in public preview (5ade755)
• update grounding metadata (d3c0a64)

Bug Fixes

• log instead of throw appendHistory errors to avoid unhandled rejection (2ec9e7d)

v1.1.0

1.1.0 (2024-04-13)

Features

• enable system instruction for GenerativeModel (590ca5a)
• enable system instruction in chat experience (7e71f75)
• exposing customHeader in requestOptions to allow users pass in customer headers. (b47d733)

v1.0.0

1.0.0 (2024-04-04)

Features

• added userAgent option to RequestOptions to allow setting User-Agent header (ca43e2f)
• include grounding metadata to stream aggregated response. (d32755e)
• Support functionCalls property in GenerationContentCandidate interface for non streaming mode (89568a6)

Bug Fixes

• check optional field in aggregate response (f7718ae)
• correct CitationMetadata interface. refactor nested function (722b7fd)
• correct code snippets in README (bdcc5fd)
• correct GenerateContentCandidate interface and GenerateContentResponse interface (7a366ab)
• correct sys test logic on stream endpoint for funcion calling (1fd5b72)
• Fix a bug in the Vertex AI client library. (8ad7dfb)
• fix bug in safetyRatings handling, fix incomplete content interfaces, and add unit test for stream response handling (e573ce6)
• for function call, role should be model. (3b80dc8)
• functionResponse should be user role (d092ab4)
• Make appendHistory private. (a1bedcd)
• pass tools from getGenerativeModel and startChat methods to top level functions (bbaf78a)
• pass tools from getGenerativeModel to chatSession. (907ad74)
• remove any type in token signature (add084c)
• remove defaulting value of candidates in unary api. remove unused variables and imports. remove throwing GoogleAIError when candidates undefined or empty. (6c0c31c)
• replace any type with explicit types in post fetch processing functions (4099129)
• replace snake_case in docs to camelCase (5893581)
• SDK should be released to 1.0.0 (4cab5fd)
• update finish reason enum list to be complete (f16b2e7)
• update prompt feedback interface (0d3754a)

v0.5.0

0.5.0 (2024-02-29)

Features

• Introduce Request Timeout Configuration (1b37f40)

Bug Fixes

• correct UsageMetadata schema (10bc676)
• include usageMetadata in stream aggregated response (a1154c9)

v0.4.0

0.4.0 (2024-02-15)

Features

• Added support for Grounding (929df39)
• enable both GA and preview namespaces. (1c2aca6)

Bug Fixes

• throw more details on error message. (5dba79c)
• unary api should only need to await once. (67a2e96)

v0.3.1

0.3.1 (2024-02-06)

Bug Fixes

• decouple dependency between VertexAI_Preivew and GenerativeModel classes (6762c99)
• Switch NodeJS generateContent to call Unary API endpoint (e4edb59)

v0.3.0

0.3.0 (2024-01-30)

Features

• add function calling support (1deb4e9)

Bug Fixes

• throw error when GoogleAuthOptions.scopes doesn't include required scope. (558aee9)
• throws instructive client side error message when bad request happens for function calling (c90203d)

v0.2.1

0.2.1 (2024-01-05)

Bug Fixes

• enable passing only a string to generateContent and generateContentStream (c50811e)

v0.2.0

0.2.0 (2024-01-03)

Features

• allow user to pass "models/model-ID" to instantiate model (e94b285)
• include all supported authentication options (257355c)

Bug Fixes

• processing of streams, including UTF (63ce032)
• remove placeholder cache attribute of access token (3ec92e7)
• update safety return types (449c7a2)
• throw ClientError or GoogleGenerativeAIError according to response status so that users can catch them and handle them according to class name. (ea0dcb7)