v0.1.152026-10-05
A patch release that replaces three retired default models, adds typed
reasoning content and OpenAI web search, and fixes a number of provider bugs.
Action required
googleai, vertex: default embedding model is now gemini-embedding-001.
embedding-001 now returns 404. The new model produces 3072-dimension
vectors that are not comparable with the old ones, so indexes built with the
old default must be re-embedded (and fixed-size vector columns resized).
googleai, vertex: default chat model is now gemini-2.5-flash.
gemini-2.0-flash is retired. Gemini 2.5 thinks by default and thinking
counts toward WithMaxTokens; a very small budget can produce no output,
which now returns ErrNoContentInResponse instead of panicking.
Multi-turn tool calling with Gemini 3 is not yet supported (it needs thought
signatures); that is planned for the next release.
anthropic: default model is now claude-sonnet-4-6.
claude-3-5-sonnet-20240620 is retired. Clients that set a model are
unaffected.
Unkeyed struct literals. No exported API was removed, but
llms.ThinkingConfig, llms.ContentChoice, llms.CallOptions and
googleai.Options gained fields, so unkeyed literals of them no longer
compile. Use keyed fields. ContentChoice JSON now includes a Parts key.
Behavior changes
- bedrock (Nova): text blocks are joined into one choice instead of one choice per block.
- mistral: non-streaming tool calls stay on the choice that made them, not Choices[0].
- googleai: an error from StreamingFunc is now returned (with a nil response).
- anthropic: reasoning-only streaming works; a stream error event ends the call;
temperature/top_p are omitted where the model or thinking mode rejects them.
- llms: ToolCall JSON round trips keep the function name and arguments;
wrongly typed fields now return a wrapped json.UnmarshalTypeError.
- llamafile: WithN and WithMinLength no longer set nctx and minp; use WithNCtx and WithMinP.
- chains: no longer clear a streaming function set by the caller.
- cohere: invalid input returns an error instead of panicking.
- googleai: GOOGLEAPIKEY is used only when no other auth option is given.
New
- llms.WithWebSearch for OpenAI (#1454).
- Typed reasoning parts: ThinkingContent, RedactedThinkingContent and ContentChoice.Parts.
- ThinkingConfig.Effort and Display (WithThinkingEffort, WithThinkingDisplay),
mapped for Anthropic and OpenAI reasoning models.
- (*ContentResponse).AssistantMessage for building the next turn of a tool loop.
- anthropic: preserves thinking and multi-part messages across turns; supports claude-fable-5.
- testing/llmtest.TestModel, a conformance check for llms.Model implementations.
Fixes
- anthropic: keep every part of system, AI and tool messages (#1456, #1468, #1010);
accept redacted_thinking blocks; replace the retired default model (#1431).
- openai: zero-argument tool schemas include properties (#1446);
reasoning_effort only for models that accept it; no temperature for search-preview models.
- googleai: send the API key with WithHTTPClient; report reasoning support for Gemini 2.5.
New Contributors
* @majiayu000 made their first contribution in https://github.com/tmc/langchaingo/pull/1454
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.14...v0.1.15
v0.1.142025-10-20
What's Changed
* anthropic: Add support for multi content part and images content in human messages. by @Neofox in https://github.com/tmc/langchaingo/pull/1141
* llms: implement StreamingReasoningFunc for reasoning models by @douglarek in https://github.com/tmc/langchaingo/pull/1125
* ci: migrate linting golangci-lint to v2.0.2 by @mdelapenya in https://github.com/tmc/langchaingo/pull/1217
* vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1204
* memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1205
* llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in https://github.com/tmc/langchaingo/pull/1238
* googleai: fix issue where gemini would ignore all but the first tool by @jpoz in https://github.com/tmc/langchaingo/pull/1244
* vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in https://github.com/tmc/langchaingo/pull/1200
* bedrock: Improve bedrock provider extraction from model id by @lucaronca in https://github.com/tmc/langchaingo/pull/1135
* duckduckgo: descriptive error message by @lmorg in https://github.com/tmc/langchaingo/pull/1260
* examples: Fix examples and complete linting upgrade by @tmc in https://github.com/tmc/langchaingo/pull/1288
* httprr: add httprr package by @tmc in https://github.com/tmc/langchaingo/pull/1296
* all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in https://github.com/tmc/langchaingo/pull/1299
* googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in https://github.com/tmc/langchaingo/pull/1292
* all: expand test coverage by @tmc in https://github.com/tmc/langchaingo/pull/1312
* docs: refactor documentation site content, structure by @tmc in https://github.com/tmc/langchaingo/pull/1311
* docs: follow-on and fix search indexing by @tmc in https://github.com/tmc/langchaingo/pull/1313
* docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in https://github.com/tmc/langchaingo/pull/1314
* vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in https://github.com/tmc/langchaingo/pull/1308
* deps: update dependencies by @tmc in https://github.com/tmc/langchaingo/pull/1319
* bedrockclient: add support for new Amazon Nova models by @oryanmoshe in https://github.com/tmc/langchaingo/pull/1083
* ollama: Fix path and align new payloads requirements by @iButcat in https://github.com/tmc/langchaingo/pull/1317
* agents: Add more robust response handling to executor.go by @xiazemin in https://github.com/tmc/langchaingo/pull/1316
* prompts: Prompt template improvements and docs expansion by @tmc in https://github.com/tmc/langchaingo/pull/1348
* ollama: Add support for reasoning mode (think parameter) by @tmc in https://github.com/tmc/langchaingo/pull/1349
* ollama: Add httprr test recordings for think parameter by @tmc in https://github.com/tmc/langchaingo/pull/1351
* llms/openai: add OpenRouter support with streaming fix by @tmc in https://github.com/tmc/langchaingo/pull/1350
* deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in https://github.com/tmc/langchaingo/pull/1352
* examples: update to use v0.1.14-pre.0 by @tmc in https://github.com/tmc/langchaingo/pull/1353
* llms/bedrock: fix whitespace formatting by @tmc in https://github.com/tmc/langchaingo/pull/1360
* llms/googleai: fix multi-tool support for Google AI and Vertex AI by @tmc in https://github.com/tmc/langchaingo/pull/1361
* vectorstores: add MariaDB and Dolt vector store implementations by @tmc in https://github.com/tmc/langchaingo/pull/1363
* agents: improve robustness of MRKL and OpenAI Functions agents by @tmc in https://github.com/tmc/langchaingo/pull/1362
* llms: fix memory and goroutine leaks in GoogleAI/Vertex and OpenAI streaming by @tmc in https://github.com/tmc/langchaingo/pull/1364
* llms/openai: improve SSE comment handling in streaming responses by @tmc in https://github.com/tmc/langchaingo/pull/1366
openai: add support for maxtokens by @kid-icarus in https://github.com/tmc/langchaingo/pull/1359
* openaiclient: add dimensions option while creating embeddings by @JLugagne in https://github.com/tmc/langchaingo/pull/1338
* llms/anthropic: allow streaming responses with tool use by @jpoz in https://github.com/tmc/langchaingo/pull/1343
* llms/bedrock: add modelProvider option and Nova model support by @dreamans in https://github.com/tmc/langchaingo/pull/1346
* googleai: ensure googleai schema conversion works with nested objects and arrays by @kid-icarus in https://github.com/tmc/langchaingo/pull/1326
* googleai: add ReasoningContent field to openai GenerateContent functio… by @topjohncian in https://github.com/tmc/langchaingo/pull/1324
* bedrock: add tool calling support for Anthropic Claude models by @manishiitg in https://github.com/tmc/langchaingo/pull/1327
* llms/bedrock: complete Anthropic tool calling support by @tmc in https://github.com/tmc/langchaingo/pull/1367
* httprr: improve test recording stability and add utilities by @tmc in https://github.com/tmc/langchaingo/pull/1368
Revert "openai: add support for maxtokens (#1359)" by @kid-icarus in https://github.com/tmc/langchaingo/pull/1369
* mongovector: fix expected error string in non-tokenized filter test by @matthewdale in https://github.com/tmc/langchaingo/pull/1331
* googleai: fix user provided embedding model getting overridden by default model by @ancalabrese in https://github.com/tmc/langchaingo/pull/1307
openai: add robust maxtokens support with backward compatibility by @tmc in https://github.com/tmc/langchaingo/pull/1371
* llms/ollama: fix panic when context is cancelled during streaming by @tmc in https://github.com/tmc/langchaingo/pull/1372
* examples: update examples to v0.1.14-pre.2 by @tmc in https://github.com/tmc/langchaingo/pull/1373
* docs: Tools Doc URL was not working by @rafian-git in https://github.com/tmc/langchaingo/pull/1309
* openai: fix temperature handling for reasoning models (GPT-5, o1, o3) by @tmc in https://github.com/tmc/langchaingo/pull/1374
* test: improve test resilience and update provider APIs by @tmc in https://github.com/tmc/langchaingo/pull/1377
* test: improve test coverage and optimize storage with gzip compression by @tmc in https://github.com/tmc/langchaingo/pull/1378
* examples: update examples to v0.1.14-pre.3 by @tmc in https://github.com/tmc/langchaingo/pull/1379
* openai: expose all available token usage details by @rainu in https://github.com/tmc/langchaingo/pull/1278
* openai: filter out open ai max token metadata by @kid-icarus in https://github.com/tmc/langchaingo/pull/1376
examples/groq: fix maxtokens compatibility issue by @tmc in https://github.com/tmc/langchaingo/pull/1382
* examples/groq: fixup groq example by @tmc in https://github.com/tmc/langchaingo/pull/1385
* internal/httprr, vectorstores/azureaisearch: fix race conditions in tests by @tmc in https://github.com/tmc/langchaingo/pull/1381
* tools/scraper: fix context cancellation hanging by @tmc in https://github.com/tmc/langchaingo/pull/1383
* agents,llms/anthropic: prevent panics in agent parsing and Anthropic responses by @tmc in https://github.com/tmc/langchaingo/pull/1380
* llms: add prompt caching and reasoning token support by @tmc in https://github.com/tmc/langchaingo/pull/1394
* tools: Add max pages limit for scraper functionality by @JJ-H in https://github.com/tmc/langchaingo/pull/1295
* vectorstores/milvus: update deprecation notice for archived SDK by @tmc in https://github.com/tmc/langchaingo/pull/1398
* docs: complete the incomplete basic chat app tutorial by @tmc in https://github.com/tmc/langchaingo/pull/1399
* examples: update to v0.1.14-pre.4 by @tmc in https://github.com/tmc/langchaingo/pull/1401
* docs: fix API r
v0.1.14-pre.3预发布2025-08-23
Pre-release v0.1.14-pre.3
Highlights
- Test suite: 100% pass rate (87/87 packages)
- Compressed test recordings with gzip
- Fixed HTTP recording compatibility issues
- Removed deprecated VertexAI PaLM support
- Updated vectorstore test recordings
What's Changed
* test: improve test resilience and update provider APIs by @tmc in https://github.com/tmc/langchaingo/pull/1377
* test: improve test coverage and optimize storage with gzip compression by @tmc in https://github.com/tmc/langchaingo/pull/1378
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.14-pre.2...v0.1.14-pre.3
v0.1.14-pre.2预发布2025-08-19
What's Changed
* llms/openai: improve SSE comment handling in streaming responses by @tmc in https://github.com/tmc/langchaingo/pull/1366
openai: add support for maxtokens by @kid-icarus in https://github.com/tmc/langchaingo/pull/1359
* openaiclient: add dimensions option while creating embeddings by @JLugagne in https://github.com/tmc/langchaingo/pull/1338
* llms/anthropic: allow streaming responses with tool use by @jpoz in https://github.com/tmc/langchaingo/pull/1343
* llms/bedrock: add modelProvider option and Nova model support by @dreamans in https://github.com/tmc/langchaingo/pull/1346
* fix: ensure googleai schema conversion works with nested objects and arrays by @kid-icarus in https://github.com/tmc/langchaingo/pull/1326
* fix: add ReasoningContent field to openai GenerateContent functio… by @topjohncian in https://github.com/tmc/langchaingo/pull/1324
* bedrock: add tool calling support for Anthropic Claude models by @manishiitg in https://github.com/tmc/langchaingo/pull/1327
* llms/bedrock: complete Anthropic tool calling support by @tmc in https://github.com/tmc/langchaingo/pull/1367
* httprr: improve test recording stability and add utilities by @tmc in https://github.com/tmc/langchaingo/pull/1368
Revert "openai: add support for maxtokens (#1359)" by @kid-icarus in https://github.com/tmc/langchaingo/pull/1369
* mongovector: fix expected error string in non-tokenized filter test by @matthewdale in https://github.com/tmc/langchaingo/pull/1331
* googleai: fix user provided embedding model getting overridden by default model by @ancalabrese in https://github.com/tmc/langchaingo/pull/1307
openai: add robust maxtokens support with backward compatibility by @tmc in https://github.com/tmc/langchaingo/pull/1371
New Contributors
* @kid-icarus made their first contribution in https://github.com/tmc/langchaingo/pull/1359
* @JLugagne made their first contribution in https://github.com/tmc/langchaingo/pull/1338
* @dreamans made their first contribution in https://github.com/tmc/langchaingo/pull/1346
* @topjohncian made their first contribution in https://github.com/tmc/langchaingo/pull/1324
* @manishiitg made their first contribution in https://github.com/tmc/langchaingo/pull/1327
* @matthewdale made their first contribution in https://github.com/tmc/langchaingo/pull/1331
* @ancalabrese made their first contribution in https://github.com/tmc/langchaingo/pull/1307
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.14-pre.1...v0.1.14-pre.2
v0.1.14-pre.1预发布2025-08-16
What's Changed
* anthropic: Add support for multi content part and images content in human messages. by @Neofox in https://github.com/tmc/langchaingo/pull/1141
* llms: implement StreamingReasoningFunc for reasoning models by @douglarek in https://github.com/tmc/langchaingo/pull/1125
* vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1204
* memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1205
* llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in https://github.com/tmc/langchaingo/pull/1238
* googleai: fix issue where gemini would ignore all but the first tool by @jpoz in https://github.com/tmc/langchaingo/pull/1244
* vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in https://github.com/tmc/langchaingo/pull/1200
* duckduckgo: descriptive error message by @lmorg in https://github.com/tmc/langchaingo/pull/1260
* httprr: add httprr package by @tmc in https://github.com/tmc/langchaingo/pull/1296
* all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in https://github.com/tmc/langchaingo/pull/1299
* googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in https://github.com/tmc/langchaingo/pull/1292
* all: expand test coverage by @tmc in https://github.com/tmc/langchaingo/pull/1312
* docs: refactor documentation site content, structure by @tmc in https://github.com/tmc/langchaingo/pull/1311
* docs: follow-on and fix search indexing by @tmc in https://github.com/tmc/langchaingo/pull/1313
* docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in https://github.com/tmc/langchaingo/pull/1314
* vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in https://github.com/tmc/langchaingo/pull/1308
* deps: update dependencies by @tmc in https://github.com/tmc/langchaingo/pull/1319
* bedrockclient: add support for new Amazon Nova models by @oryanmoshe in https://github.com/tmc/langchaingo/pull/1083
* ollama: Fix path and align new payloads requirements by @iButcat in https://github.com/tmc/langchaingo/pull/1317
* agents: Add more robust response handling to executor.go by @xiazemin in https://github.com/tmc/langchaingo/pull/1316
* prompts: Prompt template improvements and docs expansion by @tmc in https://github.com/tmc/langchaingo/pull/1348
* ollama: Add support for reasoning mode (think parameter) by @tmc in https://github.com/tmc/langchaingo/pull/1349
* ollama: Add httprr test recordings for think parameter by @tmc in https://github.com/tmc/langchaingo/pull/1351
* llms/openai: add OpenRouter support with streaming fix by @tmc in https://github.com/tmc/langchaingo/pull/1350
* deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in https://github.com/tmc/langchaingo/pull/1352
* examples: update to use v0.1.14-pre.0 by @tmc in https://github.com/tmc/langchaingo/pull/1353
* llms/bedrock: fix whitespace formatting by @tmc in https://github.com/tmc/langchaingo/pull/1360
* llms/googleai: fix multi-tool support for Google AI and Vertex AI by @tmc in https://github.com/tmc/langchaingo/pull/1361
* vectorstores: add MariaDB and Dolt vector store implementations by @coffeegoddd in https://github.com/tmc/langchaingo/pull/1363
* agents: improve robustness of MRKL and OpenAI Functions agents by @tmc in https://github.com/tmc/langchaingo/pull/1362
* llms: fix memory and goroutine leaks in GoogleAI/Vertex and OpenAI streaming by @logeable in https://github.com/tmc/langchaingo/pull/1364
New Contributors
* @Neofox made their first contribution in https://github.com/tmc/langchaingo/pull/1141
* @averikitsch made their first contribution in https://github.com/tmc/langchaingo/pull/1204
* @karsharma10 made their first contribution in https://github.com/tmc/langchaingo/pull/1238
* @jpoz made their first contribution in https://github.com/tmc/langchaingo/pull/1244
* @lmorg made their first contribution in https://github.com/tmc/langchaingo/pull/1260
* @alanrichman made their first contribution in https://github.com/tmc/langchaingo/pull/1292
* @BowieHe made their first contribution in https://github.com/tmc/langchaingo/pull/1314
* @thecoons made their first contribution in https://github.com/tmc/langchaingo/pull/1308
* @oryanmoshe made their first contribution in https://github.com/tmc/langchaingo/pull/1083
* @iButcat made their first contribution in https://github.com/tmc/langchaingo/pull/1317
* @xiazemin made their first contribution in https://github.com/tmc/langchaingo/pull/1316
* @coffeegoddd made their first contribution in https://github.com/tmc/langchaingo/pull/1363
* @logeable made their first contribution in https://github.com/tmc/langchaingo/pull/1364
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.13...v0.1.14-pre.1
v0.1.14-pre.0预发布2025-08-08
What's Changed
* anthropic: Add support for multi content part and images content in human messages. by @Neofox in https://github.com/tmc/langchaingo/pull/1141
* llms: implement StreamingReasoningFunc for reasoning models by @douglarek in https://github.com/tmc/langchaingo/pull/1125
* vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1204
* memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in https://github.com/tmc/langchaingo/pull/1205
* llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in https://github.com/tmc/langchaingo/pull/1238
* googleai: fix issue where gemini would ignore all but the first tool by @jpoz in https://github.com/tmc/langchaingo/pull/1244
* vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in https://github.com/tmc/langchaingo/pull/1200
* duckduckgo: descriptive error message by @lmorg in https://github.com/tmc/langchaingo/pull/1260
* httprr: add httprr package by @tmc in https://github.com/tmc/langchaingo/pull/1296
* all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in https://github.com/tmc/langchaingo/pull/1299
* googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in https://github.com/tmc/langchaingo/pull/1292
* all: expand test coverage by @tmc in https://github.com/tmc/langchaingo/pull/1312
* docs: refactor documentation site content, structure by @tmc in https://github.com/tmc/langchaingo/pull/1311
* docs: follow-on and fix search indexing by @tmc in https://github.com/tmc/langchaingo/pull/1313
* docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in https://github.com/tmc/langchaingo/pull/1314
* vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in https://github.com/tmc/langchaingo/pull/1308
* deps: update dependencies by @tmc in https://github.com/tmc/langchaingo/pull/1319
* bedrockclient: add support for new Amazon Nova models by @oryanmoshe in https://github.com/tmc/langchaingo/pull/1083
* ollama: Fix path and align new payloads requirements by @iButcat in https://github.com/tmc/langchaingo/pull/1317
* agents: Add more robust response handling to executor.go by @xiazemin in https://github.com/tmc/langchaingo/pull/1316
* prompts: Prompt template improvements and docs expansion by @tmc in https://github.com/tmc/langchaingo/pull/1348
* ollama: Add support for reasoning mode (think parameter) by @tmc in https://github.com/tmc/langchaingo/pull/1349
* ollama: Add httprr test recordings for think parameter by @tmc in https://github.com/tmc/langchaingo/pull/1351
* llms/openai: add OpenRouter support with streaming fix by @tmc in https://github.com/tmc/langchaingo/pull/1350
* deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in https://github.com/tmc/langchaingo/pull/1352
New Contributors
* @Neofox made their first contribution in https://github.com/tmc/langchaingo/pull/1141
* @averikitsch made their first contribution in https://github.com/tmc/langchaingo/pull/1204
* @karsharma10 made their first contribution in https://github.com/tmc/langchaingo/pull/1238
* @jpoz made their first contribution in https://github.com/tmc/langchaingo/pull/1244
* @lmorg made their first contribution in https://github.com/tmc/langchaingo/pull/1260
* @alanrichman made their first contribution in https://github.com/tmc/langchaingo/pull/1292
* @BowieHe made their first contribution in https://github.com/tmc/langchaingo/pull/1314
* @thecoons made their first contribution in https://github.com/tmc/langchaingo/pull/1308
* @oryanmoshe made their first contribution in https://github.com/tmc/langchaingo/pull/1083
* @iButcat made their first contribution in https://github.com/tmc/langchaingo/pull/1317
* @xiazemin made their first contribution in https://github.com/tmc/langchaingo/pull/1316
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.13...v0.1.14-pre.0
v0.1.132025-02-16
v0.1.13 Release Notes
Highlight: MongoDB Vector Store Integration
We're excited to announce full MongoDB vector store support, one of our most requested features!
* Complete MongoDB vector store implementation with production-ready features
* Comprehensive documentation and examples
* Containerized testing suite for reliability
* Upgraded to mongo-go-driver v2.0.0 for improved performance
* Thanks to @prestonvasquez for this significant contribution!
Major Features & Improvements
* Added Mistral embeddings support with PGVector example by @mathiasb
* Added Perplexity AI tool integration by @sklinkert
* Added support for OpenAI structured output and image+text content by @lifejwang11
* Added fake LLM package for testing by @devalexandre
Provider Updates
OpenAI
Reflected maxtoken field deprecation
Added completiontokens_details to usage response
* Added reasoning tokens support for both regular and streaming responses
* Added O1-preview example and documentation
Google AI
* Added system instructions support for Vertex
* Added JSONMode and ResponseMIMEType support
* Improved test resilience for model randomness
Anthropic
* Added beta header support
* Improved error event type handling
Mistral
* Updated dependency version
* Added support for default llms.WithTools implementation
DeepSeek
* Added ReasoningContent field for reasoner model by @semioz
Breaking Changes
* Upgraded to mongo-go-driver v2.0.0
* Replaced deprecated agents.Initialize in examples
Detailed Changelog
What's Changed
* googleai: add support for system instructions in vertex too by @eliben in https://github.com/tmc/langchaingo/pull/930
* googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in https://github.com/tmc/langchaingo/pull/936
* googleai: update dependency version by @eliben in https://github.com/tmc/langchaingo/pull/939
* anthropic: add support for beta header by @tmc in https://github.com/tmc/langchaingo/pull/967
* anthropic: add improved handling of other error event types by @tmc in https://github.com/tmc/langchaingo/pull/1012
openai: reflect maxtoken field deprecation by @tmc in https://github.com/tmc/langchaingo/pull/1013
openai: add completiontokens_details to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1014
* openai: add reasoning tokens to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1015
* openai: add reasoning tokens to streaming response by @tmc in https://github.com/tmc/langchaingo/pull/1016
* examples: add openai o1-preview example by @tmc in https://github.com/tmc/langchaingo/pull/1017
* examples: improve o1 readme by @tmc in https://github.com/tmc/langchaingo/pull/1020
* examples: update to v0.1.13-pre.0 by @tmc in https://github.com/tmc/langchaingo/pull/1021
* llms: fix unkeyed fields in GenerateFromSinglePrompt struct by @iocron in https://github.com/tmc/langchaingo/pull/926
* ci: upgrade golangci lint version by @wangjiancn in https://github.com/tmc/langchaingo/pull/928
* examples: add perplexity completion example by @sklinkert in https://github.com/tmc/langchaingo/pull/977
* agents: optimize the mrkl prompt by @Alan796 in https://github.com/tmc/langchaingo/pull/976
* docs: fix Type method missing from OutputParser by @chxru in https://github.com/tmc/langchaingo/pull/972
* outputparser: improve BooleanOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/978
* outputparser: improve DefinedOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/980
* textsplitter: add option to join table rows by @corani in https://github.com/tmc/langchaingo/pull/981
* googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in https://github.com/tmc/langchaingo/pull/984
* openai: add support for sending structured output request for chat completions api by @takeyamakenta in https://github.com/tmc/langchaingo/pull/986
* redisvector: fix score threshold option by @acrmp in https://github.com/tmc/langchaingo/pull/1003
* milvus: add skipFlushOnWrite option by @fatedier in https://github.com/tmc/langchaingo/pull/992
* outputparser: use strings.Cut in structured parser by @anuraaga in https://github.com/tmc/langchaingo/pull/997
* examples: replace deprecated agents.Initialize by @treywelsh in https://github.com/tmc/langchaingo/pull/1009
* bedrock: fix unchecked error when stream channel is closed by @lucaronca in https://github.com/tmc/langchaingo/pull/998
* llms: add fake package by @devalexandre in https://github.com/tmc/langchaingo/pull/935
* examples: update pgvector README to use compose v2 by @elnoro in https://github.com/tmc/langchaingo/pull/969
* llms/mistral: add support for default WithTools implementation by @douglarek in https://github.com/tmc/langchaingo/pull/970
* vectorstores: add mongovector by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1005
* lint: fix settings and refactor package by @tmc in https://github.com/tmc/langchaingo/pull/1018
* vectorstores: fix cosine similarity score calculation by @avi3tal in https://github.com/tmc/langchaingo/pull/1048
* internal: fix data races by @nktks in https://github.com/tmc/langchaingo/pull/1080
* tools: add perplexity AI by @sklinkert in https://github.com/tmc/langchaingo/pull/1061
* vectorstores/weaviate,pinecone: do not return error when zero documents are retrieved by @mdelapenya in https://github.com/tmc/langchaingo/pull/1077
* examples: add OpenAI json structured example by @lifejwang11 in https://github.com/tmc/langchaingo/pull/1098
* textsplitter: add optional lenFunc to MarkdownTextSplitter by @pedramr in https://github.com/tmc/langchaingo/pull/1096
* llms/mistral: implement embeddings.EmbedderClient for Mistral and add PGVector example by @mathiasb in https://github.com/tmc/langchaingo/pull/1086
* vectorstores/weaviate: fix client creator by @taigrr in https://github.com/tmc/langchaingo/pull/1109
* examples: add image and text content example for openai by @lifejwang11 in https://github.com/tmc/langchaingo/pull/1099
* test: containerize mongovector tests by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1025
* deps: update mistral go version by @fstau in https://github.com/tmc/langchaingo/pull/1102
* deps: upgrade to mongo-go-driver v2.0.0 by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1087
* docs: update Discord invite link in README by @danielmerja in https://github.com/tmc/langchaingo/pull/1118
* docs: add mongovector README and example by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1063
* llms/deepseek: add ReasoningContent field for reasoner model by @semioz in https://github.com/tmc/langchaingo/pull/1121
* docs: fix documentation publishing by @FluffyKebab in https://github.com/tmc/langchaingo/pull/1123
* docs: fix artifact upload in documentation publishing by @FluffyKebab in https://github.com/tmc/langchaingo/pull/1124
New Contributors
* @iocron made their first contribution in https://github.com/tmc/langchaingo/pull/926
* @Alan796 made their first contribution in https://github.com/tmc/langchaingo/pull/976
* @chxru made their first contribution in https://github.com/tmc/langchaingo/pull/972
* @amitaifrey made their first contribution in https://github.com/tmc/langchaingo/pull/978
* @mheck136 made their first contribution in https://github.com/tmc/langchaingo/pull/984
* @takeyamakenta made their first contribution in https://github.com/tmc/langchaingo/pull/986
* @acrmp made their first contribution in https://github.com/tmc/langchaingo/pull/1003
* @anuraaga made their first contribution in https://github.com/tmc/langchaingo/pull/997
* @treywelsh made their first contribution in https://github.com/tmc/langchaingo/pull/1009
* @lucaronca made their first contribution in https://github.com/tmc/langchaingo/pull/998
* @prestonvasquez made their first contrib
v0.1.13-pre.1预发布2025-02-05
What's Changed
* googleai: add support for system instructions in vertex too by @eliben in https://github.com/tmc/langchaingo/pull/930
* googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in https://github.com/tmc/langchaingo/pull/936
* googleai: update dependency version by @eliben in https://github.com/tmc/langchaingo/pull/939
* anthropic: add support for beta header by @tmc in https://github.com/tmc/langchaingo/pull/967
* anthropic: add improved handling of other error event types by @tmc in https://github.com/tmc/langchaingo/pull/1012
openai: reflect maxtoken field deprecation by @tmc in https://github.com/tmc/langchaingo/pull/1013
openai: add completiontokens_details to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1014
* openai: add reasoning tokens to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1015
* openai: add reasoning tokens to streaming response by @tmc in https://github.com/tmc/langchaingo/pull/1016
* examples: add openai o1-preview example by @tmc in https://github.com/tmc/langchaingo/pull/1017
* examples: improve o1 readme by @tmc in https://github.com/tmc/langchaingo/pull/1020
* examples: update to v0.1.13-pre.0 by @tmc in https://github.com/tmc/langchaingo/pull/1021
* llms: fix unkeyed fields in GenerateFromSinglePrompt struct by @iocron in https://github.com/tmc/langchaingo/pull/926
* ci: upgrade golangci lint version by @wangjiancn in https://github.com/tmc/langchaingo/pull/928
* examples: add perplexity completion example by @sklinkert in https://github.com/tmc/langchaingo/pull/977
* agents: optimize the mrkl prompt by @Alan796 in https://github.com/tmc/langchaingo/pull/976
* docs: fix Type method missing from OutputParser by @chxru in https://github.com/tmc/langchaingo/pull/972
* outputparser: improve BooleanOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/978
* outputparser: improve DefinedOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/980
* textsplitter: add option to join table rows by @corani in https://github.com/tmc/langchaingo/pull/981
* googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in https://github.com/tmc/langchaingo/pull/984
* openai: add support for sending structured output request for chat completions api by @takeyamakenta in https://github.com/tmc/langchaingo/pull/986
* redisvector: fix score threshold option by @acrmp in https://github.com/tmc/langchaingo/pull/1003
* milvus: add skipFlushOnWrite option by @fatedier in https://github.com/tmc/langchaingo/pull/992
* outputparser: use strings.Cut in structured parser by @anuraaga in https://github.com/tmc/langchaingo/pull/997
* examples: replace deprecated agents.Initialize by @treywelsh in https://github.com/tmc/langchaingo/pull/1009
* bedrock: fix unchecked error when stream channel is closed by @lucaronca in https://github.com/tmc/langchaingo/pull/998
* llms: add fake package by @devalexandre in https://github.com/tmc/langchaingo/pull/935
* examples: update pgvector README to use compose v2 by @elnoro in https://github.com/tmc/langchaingo/pull/969
* llms/mistral: add support for default WithTools implementation by @douglarek in https://github.com/tmc/langchaingo/pull/970
* vectorstores: add mongovector by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1005
* lint: fix settings and refactor package by @tmc in https://github.com/tmc/langchaingo/pull/1018
* vectorstores: fix cosine similarity score calculation by @avi3tal in https://github.com/tmc/langchaingo/pull/1048
* internal: fix data races by @nktks in https://github.com/tmc/langchaingo/pull/1080
* tools: add perplexity AI by @sklinkert in https://github.com/tmc/langchaingo/pull/1061
* vectorstores/weaviate,pinecone: do not return error when zero documents are retrieved by @mdelapenya in https://github.com/tmc/langchaingo/pull/1077
* examples: add OpenAI json structured example by @lifejwang11 in https://github.com/tmc/langchaingo/pull/1098
* textsplitter: add optional lenFunc to MarkdownTextSplitter by @pedramr in https://github.com/tmc/langchaingo/pull/1096
* llms/mistral: implement embeddings.EmbedderClient for Mistral and add PGVector example by @mathiasb in https://github.com/tmc/langchaingo/pull/1086
* vectorstores/weaviate: fix client creator by @taigrr in https://github.com/tmc/langchaingo/pull/1109
* examples: add image and text content example for openai by @lifejwang11 in https://github.com/tmc/langchaingo/pull/1099
* test: containerize mongovector tests by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1025
* deps: update mistral go version by @fstau in https://github.com/tmc/langchaingo/pull/1102
* deps: upgrade to mongo-go-driver v2.0.0 by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1087
* docs: update Discord invite link in README by @danielmerja in https://github.com/tmc/langchaingo/pull/1118
* docs: add mongovector README and example by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1063
* llms/deepseek: add ReasoningContent field for reasoner model by @semioz in https://github.com/tmc/langchaingo/pull/1121
* docs: fix documentation publishing by @FluffyKebab in https://github.com/tmc/langchaingo/pull/1123
* docs: fix artifact upload in documentation publishing by @FluffyKebab in https://github.com/tmc/langchaingo/pull/1124
New Contributors
* @iocron made their first contribution in https://github.com/tmc/langchaingo/pull/926
* @Alan796 made their first contribution in https://github.com/tmc/langchaingo/pull/976
* @chxru made their first contribution in https://github.com/tmc/langchaingo/pull/972
* @amitaifrey made their first contribution in https://github.com/tmc/langchaingo/pull/978
* @mheck136 made their first contribution in https://github.com/tmc/langchaingo/pull/984
* @takeyamakenta made their first contribution in https://github.com/tmc/langchaingo/pull/986
* @acrmp made their first contribution in https://github.com/tmc/langchaingo/pull/1003
* @anuraaga made their first contribution in https://github.com/tmc/langchaingo/pull/997
* @treywelsh made their first contribution in https://github.com/tmc/langchaingo/pull/1009
* @lucaronca made their first contribution in https://github.com/tmc/langchaingo/pull/998
* @prestonvasquez made their first contribution in https://github.com/tmc/langchaingo/pull/1005
* @avi3tal made their first contribution in https://github.com/tmc/langchaingo/pull/1048
* @nktks made their first contribution in https://github.com/tmc/langchaingo/pull/1080
* @lifejwang11 made their first contribution in https://github.com/tmc/langchaingo/pull/1098
* @pedramr made their first contribution in https://github.com/tmc/langchaingo/pull/1096
* @mathiasb made their first contribution in https://github.com/tmc/langchaingo/pull/1086
* @taigrr made their first contribution in https://github.com/tmc/langchaingo/pull/1109
* @fstau made their first contribution in https://github.com/tmc/langchaingo/pull/1102
* @danielmerja made their first contribution in https://github.com/tmc/langchaingo/pull/1118
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.12...v0.1.13-pre.1
v0.1.13-pre.0预发布2024-09-13
What's Changed
* googleai: add support for system instructions in vertex too by @eliben in https://github.com/tmc/langchaingo/pull/930
* googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in https://github.com/tmc/langchaingo/pull/936
* googleai: update dependency version by @eliben in https://github.com/tmc/langchaingo/pull/939
* anthropic: Add support for beta header by @tmc in https://github.com/tmc/langchaingo/pull/967
* anthropic: Add improved handling of other error event types by @tmc in https://github.com/tmc/langchaingo/pull/1012
openai: reflect maxtoken field deprecation by @tmc in https://github.com/tmc/langchaingo/pull/1013
openai: add completiontokens_details to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1014
* openai: add reasoning tokens to usage response by @tmc in https://github.com/tmc/langchaingo/pull/1015
* openai: add reasoning tokens to streaming response by @tmc in https://github.com/tmc/langchaingo/pull/1016
* examples: Add openai o1-preview example by @tmc in https://github.com/tmc/langchaingo/pull/1017
* llms: GenerateFromSinglePrompt struct literal uses unkeyed fields by @iocron in https://github.com/tmc/langchaingo/pull/926
* ci: upgrade golangci lint version by @wangjiancn in https://github.com/tmc/langchaingo/pull/928
* Add perplexity completion example by @sklinkert in https://github.com/tmc/langchaingo/pull/977
* agents: optimize the mrkl prompt by @Alan796 in https://github.com/tmc/langchaingo/pull/976
* fix(docs): Type method missing from OutputParser by @chxru in https://github.com/tmc/langchaingo/pull/972
* outputparser: improve BooleanOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/978
* outputparser: improve DefinedOutputParser by @amitaifrey in https://github.com/tmc/langchaingo/pull/980
* textsplitter: add option to join table rows by @corani in https://github.com/tmc/langchaingo/pull/981
* googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in https://github.com/tmc/langchaingo/pull/984
* openai: add support for sending Structured Output request for chat completions api by @takeyamakenta in https://github.com/tmc/langchaingo/pull/986
* redisvector: fix score threshold option by @acrmp in https://github.com/tmc/langchaingo/pull/1003
* milvus: add skipFlushOnWrite option by @fatedier in https://github.com/tmc/langchaingo/pull/992
* outputparser: use strings.Cut in structured parser by @anuraaga in https://github.com/tmc/langchaingo/pull/997
* examples: replace deprecated agents.Initialize by @treywelsh in https://github.com/tmc/langchaingo/pull/1009
* bedrock: Fix unchecked error when stream channel is closed by @lucaronca in https://github.com/tmc/langchaingo/pull/998
* llms: Add fake package by @devalexandre in https://github.com/tmc/langchaingo/pull/935
* examples: replaced compose v1 with compose v2 in readme for pgvector example by @elnoro in https://github.com/tmc/langchaingo/pull/969
* fix(mistral): supports the default llms.WithTools implementation by @douglarek in https://github.com/tmc/langchaingo/pull/970
* vectorstores: add mongovector by @prestonvasquez in https://github.com/tmc/langchaingo/pull/1005
* lint: fixup lint settings, refactor package by @tmc in https://github.com/tmc/langchaingo/pull/1018
New Contributors
* @iocron made their first contribution in https://github.com/tmc/langchaingo/pull/926
* @Alan796 made their first contribution in https://github.com/tmc/langchaingo/pull/976
* @chxru made their first contribution in https://github.com/tmc/langchaingo/pull/972
* @amitaifrey made their first contribution in https://github.com/tmc/langchaingo/pull/978
* @mheck136 made their first contribution in https://github.com/tmc/langchaingo/pull/984
* @takeyamakenta made their first contribution in https://github.com/tmc/langchaingo/pull/986
* @acrmp made their first contribution in https://github.com/tmc/langchaingo/pull/1003
* @anuraaga made their first contribution in https://github.com/tmc/langchaingo/pull/997
* @treywelsh made their first contribution in https://github.com/tmc/langchaingo/pull/1009
* @lucaronca made their first contribution in https://github.com/tmc/langchaingo/pull/998
* @prestonvasquez made their first contribution in https://github.com/tmc/langchaingo/pull/1005
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.12...v0.1.13-pre.0
v0.1.122024-06-21
What's Changed
* llms/googleai: fix vertex do not return usage info by @wangjiancn in https://github.com/tmc/langchaingo/pull/904
* bugfix: Anthropic Function Calling by @lwlee2608 in https://github.com/tmc/langchaingo/pull/899
* llms/anthropic: Fix Content set incorrectly for anthropic llm requests by @JckHoe in https://github.com/tmc/langchaingo/pull/908
* llms/googleai: fix convert tool error by @wangjiancn in https://github.com/tmc/langchaingo/pull/903
* llms/googleai: Fix usage population tests, max token test, update dpep by @tmc in https://github.com/tmc/langchaingo/pull/910
* docs/groq: by @devalexandre in https://github.com/tmc/langchaingo/pull/907
* llms/watsonx: update module by @h0rv in https://github.com/tmc/langchaingo/pull/902
docs: fix textsplitters mdx code example never closed by @4lxprime in https://github.com/tmc/langchaingo/pull/900
* textsplitter: add WithHeadingHierarchy option to markdown splitter to retain heading hierarchy in chunks by @iwilltry42 in https://github.com/tmc/langchaingo/pull/898
* examples: point watsonx example at current main by @tmc in https://github.com/tmc/langchaingo/pull/911
* outputparser: add Defined parser to extract a struct from LLM output by @erictse in https://github.com/tmc/langchaingo/pull/856
* anthropic: Improve streaming message handling in anthropic client by @tmc in https://github.com/tmc/langchaingo/pull/912
googleai: Settle on GOOGLEAPI_KEY for google auth env var name by @tmc in https://github.com/tmc/langchaingo/pull/913
* llms: Increase default tokens by @tmc in https://github.com/tmc/langchaingo/pull/914
* examples: Add example readmes by @tmc in https://github.com/tmc/langchaingo/pull/916
* examples: Improve top level readme by @tmc in https://github.com/tmc/langchaingo/pull/919
* anthropic: Spruce up tool calling example by @tmc in https://github.com/tmc/langchaingo/pull/921
* examples: point to 0.1.12-pre.0 by @tmc in https://github.com/tmc/langchaingo/pull/922
New Contributors
* @JckHoe made their first contribution in https://github.com/tmc/langchaingo/pull/908
* @4lxprime made their first contribution in https://github.com/tmc/langchaingo/pull/900
* @iwilltry42 made their first contribution in https://github.com/tmc/langchaingo/pull/898
* @erictse made their first contribution in https://github.com/tmc/langchaingo/pull/856
Full Changelog: https://github.com/tmc/langchaingo/compare/v0.1.11...v0.1.12