v0.1.14

What's Changed

• anthropic: Add support for multi content part and images content in human messages. by @Neofox in #1141
• llms: implement StreamingReasoningFunc for reasoning models by @douglarek in #1125
• ci: migrate linting golangci-lint to v2.0.2 by @mdelapenya in #1217
• vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1204
• memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1205
• llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in #1238
• googleai: fix issue where gemini would ignore all but the first tool by @jpoz in #1244
• vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in #1200
• bedrock: Improve bedrock provider extraction from model id by @lucaronca in #1135
• duckduckgo: descriptive error message by @lmorg in #1260
• examples: Fix examples and complete linting upgrade by @tmc in #1288
• httprr: add httprr package by @tmc in #1296
• all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in #1299
• googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in #1292
• all: expand test coverage by @tmc in #1312
• docs: refactor documentation site content, structure by @tmc in #1311
• docs: follow-on and fix search indexing by @tmc in #1313
• docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in #1314
• vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in #1308
• deps: update dependencies by @tmc in #1319
• bedrockclient: add support for new Amazon Nova models by @oryanmoshe in #1083
• ollama: Fix path and align new payloads requirements by @iButcat in #1317
• agents: Add more robust response handling to executor.go by @xiazemin in #1316
• prompts: Prompt template improvements and docs expansion by @tmc in #1348
• ollama: Add support for reasoning mode (think parameter) by @tmc in #1349
• ollama: Add httprr test recordings for think parameter by @tmc in #1351
• llms/openai: add OpenRouter support with streaming fix by @tmc in #1350
• deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in #1352
• examples: update to use v0.1.14-pre.0 by @tmc in #1353
• llms/bedrock: fix whitespace formatting by @tmc in #1360
• llms/googleai: fix multi-tool support for Google AI and Vertex AI by @tmc in #1361
• vectorstores: add MariaDB and Dolt vector store implementations by @tmc in #1363
• agents: improve robustness of MRKL and OpenAI Functions agents by @tmc in #1362
• llms: fix memory and goroutine leaks in GoogleAI/Vertex and OpenAI streaming by @tmc in #1364
• llms/openai: improve SSE comment handling in streaming responses by @tmc in #1366
• openai: add support for max_tokens by @kid-icarus in #1359
• openaiclient: add dimensions option while creating embeddings by @JLugagne in #1338
• llms/anthropic: allow streaming responses with tool use by @jpoz in #1343
• llms/bedrock: add modelProvider option and Nova model support by @dreamans in #1346
• googleai: ensure googleai schema conversion works with nested objects and arrays by @kid-icarus in #1326
• googleai: add ReasoningContent field to openai GenerateContent functio… by @topjohncian in #1324
• bedrock: add tool calling support for Anthropic Claude models by @manishiitg in #1327
• llms/bedrock: complete Anthropic tool calling support by @tmc in #1367
• httprr: improve test recording stability and add utilities by @tmc in #1368
• Revert "openai: add support for max_tokens (#1359)" by @kid-icarus in #1369
• mongovector: fix expected error string in non-tokenized filter test by @matthewdale in #1331
• googleai: fix user provided embedding model getting overridden by default model by @ancalabrese in #1307
• openai: add robust max_tokens support with backward compatibility by @tmc in #1371
• llms/ollama: fix panic when context is cancelled during streaming by @tmc in #1372
• examples: update examples to v0.1.14-pre.2 by @tmc in #1373
• docs: Tools Doc URL was not working by @rafian-git in #1309
• openai: fix temperature handling for reasoning models (GPT-5, o1, o3) by @tmc in #1374
• test: improve test resilience and update provider APIs by @tmc in #1377
• test: improve test coverage and optimize storage with gzip compression by @tmc in #1378
• examples: update examples to v0.1.14-pre.3 by @tmc in #1379
• openai: expose all available token usage details by @rainu in #1278
• openai: filter out open ai max token metadata by @kid-icarus in #1376
• examples/groq: fix max_tokens compatibility issue by @tmc in #1382
• examples/groq: fixup groq example by @tmc in #1385
• internal/httprr, vectorstores/azureaisearch: fix race conditions in tests by @tmc in #1381
• tools/scraper: fix context cancellation hanging by @tmc in #1383
• agents,llms/anthropic: prevent panics in agent parsing and Anthropic responses by @tmc in #1380
• llms: add prompt caching and reasoning token support by @tmc in #1394
• tools: Add max pages limit for scraper functionality by @JJ-H in #1295
• vectorstores/milvus: update deprecation notice for archived SDK by @tmc in #1398
• docs: complete the incomplete basic chat app tutorial by @tmc in #1399
• examples: update to v0.1.14-pre.4 by @tmc in #1401
• docs: fix API references and complete integration documentation by @tmc in #1402
• examples: fix typo in openai-chat-example.go of maximum tokens per generation, old: 104 tokens, fix: 1024 tokens by @SSSKrut in #1392
• llms: update model context sizes for GPT-4o and GPT-4 Turbo by @paulnegz in #1389
• documentloaders: add RecursiveDirectoryLoader that loads documents with allowed extensions from a directory by @zhu733756 in #1386
• httputil: enhance JSONDebugClient with SSE and header debugging by @tmc in #1404
• vectorstores/milvus: complete migration to new SDK v2 client by @tmc in #1403
• anthropic: add improved streaming thinking/reasoning token support by @tmc in #1418
• agents: fix ChainCallOption silent failure by @tmc in #1420
• llms/openai: sanitize HTTP errors to prevent API key exposure by @tmc in #1419
• agents: allow match from multiple lines for parseOutput function by @hemarina in #1415

New Contributors

• @Neofox made their first contribution in #1141
• @averikitsch made their first contribution in #1204
• @karsharma10 made their first contribution in #1238
• @jpoz made their first contribution in #1244
• @lmorg made their first contribution in #1260
• @alanrichman made their first contribution in #1292
• @BowieHe made their first contribution in #1314
• @thecoons made their first contribut...

v0.1.14-pre.3

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 #1377
• test: improve test coverage and optimize storage with gzip compression by @tmc in #1378

Full Changelog: v0.1.14-pre.2...v0.1.14-pre.3

v0.1.14-pre.2

What's Changed

• llms/openai: improve SSE comment handling in streaming responses by @tmc in #1366
• openai: add support for max_tokens by @kid-icarus in #1359
• openaiclient: add dimensions option while creating embeddings by @JLugagne in #1338
• llms/anthropic: allow streaming responses with tool use by @jpoz in #1343
• llms/bedrock: add modelProvider option and Nova model support by @dreamans in #1346
• fix: ensure googleai schema conversion works with nested objects and arrays by @kid-icarus in #1326
• fix: add ReasoningContent field to openai GenerateContent functio… by @topjohncian in #1324
• bedrock: add tool calling support for Anthropic Claude models by @manishiitg in #1327
• llms/bedrock: complete Anthropic tool calling support by @tmc in #1367
• httprr: improve test recording stability and add utilities by @tmc in #1368
• Revert "openai: add support for max_tokens (#1359)" by @kid-icarus in #1369
• mongovector: fix expected error string in non-tokenized filter test by @matthewdale in #1331
• googleai: fix user provided embedding model getting overridden by default model by @ancalabrese in #1307
• openai: add robust max_tokens support with backward compatibility by @tmc in #1371

New Contributors

• @kid-icarus made their first contribution in #1359
• @JLugagne made their first contribution in #1338
• @dreamans made their first contribution in #1346
• @topjohncian made their first contribution in #1324
• @manishiitg made their first contribution in #1327
• @matthewdale made their first contribution in #1331
• @ancalabrese made their first contribution in #1307

Full Changelog: v0.1.14-pre.1...v0.1.14-pre.2

v0.1.14-pre.1

What's Changed

• anthropic: Add support for multi content part and images content in human messages. by @Neofox in #1141
• llms: implement StreamingReasoningFunc for reasoning models by @douglarek in #1125
• vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1204
• memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1205
• llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in #1238
• googleai: fix issue where gemini would ignore all but the first tool by @jpoz in #1244
• vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in #1200
• duckduckgo: descriptive error message by @lmorg in #1260
• httprr: add httprr package by @tmc in #1296
• all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in #1299
• googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in #1292
• all: expand test coverage by @tmc in #1312
• docs: refactor documentation site content, structure by @tmc in #1311
• docs: follow-on and fix search indexing by @tmc in #1313
• docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in #1314
• vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in #1308
• deps: update dependencies by @tmc in #1319
• bedrockclient: add support for new Amazon Nova models by @oryanmoshe in #1083
• ollama: Fix path and align new payloads requirements by @iButcat in #1317
• agents: Add more robust response handling to executor.go by @xiazemin in #1316
• prompts: Prompt template improvements and docs expansion by @tmc in #1348
• ollama: Add support for reasoning mode (think parameter) by @tmc in #1349
• ollama: Add httprr test recordings for think parameter by @tmc in #1351
• llms/openai: add OpenRouter support with streaming fix by @tmc in #1350
• deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in #1352
• examples: update to use v0.1.14-pre.0 by @tmc in #1353
• llms/bedrock: fix whitespace formatting by @tmc in #1360
• llms/googleai: fix multi-tool support for Google AI and Vertex AI by @tmc in #1361
• vectorstores: add MariaDB and Dolt vector store implementations by @coffeegoddd in #1363
• agents: improve robustness of MRKL and OpenAI Functions agents by @tmc in #1362
• llms: fix memory and goroutine leaks in GoogleAI/Vertex and OpenAI streaming by @logeable in #1364

New Contributors

• @Neofox made their first contribution in #1141
• @averikitsch made their first contribution in #1204
• @karsharma10 made their first contribution in #1238
• @jpoz made their first contribution in #1244
• @lmorg made their first contribution in #1260
• @alanrichman made their first contribution in #1292
• @BowieHe made their first contribution in #1314
• @thecoons made their first contribution in #1308
• @oryanmoshe made their first contribution in #1083
• @iButcat made their first contribution in #1317
• @xiazemin made their first contribution in #1316
• @coffeegoddd made their first contribution in #1363
• @logeable made their first contribution in #1364

Full Changelog: v0.1.13...v0.1.14-pre.1

v0.1.14-pre.0

What's Changed

• anthropic: Add support for multi content part and images content in human messages. by @Neofox in #1141
• llms: implement StreamingReasoningFunc for reasoning models by @douglarek in #1125
• vectorstore: Add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1204
• memory: add interfaces for Google AlloyDB and Cloud SQL by @averikitsch in #1205
• llms/openai: replace deprecated gpt-4-vision-preview with gpt-4o in TestMultiContentImage by @karsharma10 in #1238
• googleai: fix issue where gemini would ignore all but the first tool by @jpoz in #1244
• vectorstores: add Bedrock Knowledge Bases vectorstore support by @lucaronca in #1200
• duckduckgo: descriptive error message by @lmorg in #1260
• httprr: add httprr package by @tmc in #1296
• all: add broad httprr coverage, update dependencies, organize go.mod file, bump to 1.23 by @tmc in #1299
• googleai: Replace textembedding-gecko with text-embedding-005 in its PaLM Client by @alanrichman in #1292
• all: expand test coverage by @tmc in #1312
• docs: refactor documentation site content, structure by @tmc in #1311
• docs: follow-on and fix search indexing by @tmc in #1313
• docs:fix typo error, openAI and anthropic use withToken instead of wi… by @BowieHe in #1314
• vectorstores: add WithEndpoint option for Azure AI Search by @thecoons in #1308
• deps: update dependencies by @tmc in #1319
• bedrockclient: add support for new Amazon Nova models by @oryanmoshe in #1083
• ollama: Fix path and align new payloads requirements by @iButcat in #1317
• agents: Add more robust response handling to executor.go by @xiazemin in #1316
• prompts: Prompt template improvements and docs expansion by @tmc in #1348
• ollama: Add support for reasoning mode (think parameter) by @tmc in #1349
• ollama: Add httprr test recordings for think parameter by @tmc in #1351
• llms/openai: add OpenRouter support with streaming fix by @tmc in #1350
• deps: update Go version to 1.23.8 and toolchain to 1.24.6 by @tmc in #1352

New Contributors

• @Neofox made their first contribution in #1141
• @averikitsch made their first contribution in #1204
• @karsharma10 made their first contribution in #1238
• @jpoz made their first contribution in #1244
• @lmorg made their first contribution in #1260
• @alanrichman made their first contribution in #1292
• @BowieHe made their first contribution in #1314
• @thecoons made their first contribution in #1308
• @oryanmoshe made their first contribution in #1083
• @iButcat made their first contribution in #1317
• @xiazemin made their first contribution in #1316

Full Changelog: v0.1.13...v0.1.14-pre.0

v0.1.13

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 max_token field deprecation
• Added completion_tokens_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 #930
• googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in #936
• googleai: update dependency version by @eliben in #939
• anthropic: add support for beta header by @tmc in #967
• anthropic: add improved handling of other error event types by @tmc in #1012
• openai: reflect max_token field deprecation by @tmc in #1013
• openai: add completion_tokens_details to usage response by @tmc in #1014
• openai: add reasoning tokens to usage response by @tmc in #1015
• openai: add reasoning tokens to streaming response by @tmc in #1016
• examples: add openai o1-preview example by @tmc in #1017
• examples: improve o1 readme by @tmc in #1020
• examples: update to v0.1.13-pre.0 by @tmc in #1021
• llms: fix unkeyed fields in GenerateFromSinglePrompt struct by @iocron in #926
• ci: upgrade golangci lint version by @wangjiancn in #928
• examples: add perplexity completion example by @sklinkert in #977
• agents: optimize the mrkl prompt by @Alan796 in #976
• docs: fix Type method missing from OutputParser by @chxru in #972
• outputparser: improve BooleanOutputParser by @amitaifrey in #978
• outputparser: improve DefinedOutputParser by @amitaifrey in #980
• textsplitter: add option to join table rows by @corani in #981
• googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in #984
• openai: add support for sending structured output request for chat completions api by @takeyamakenta in #986
• redisvector: fix score threshold option by @acrmp in #1003
• milvus: add skipFlushOnWrite option by @fatedier in #992
• outputparser: use strings.Cut in structured parser by @anuraaga in #997
• examples: replace deprecated agents.Initialize by @treywelsh in #1009
• bedrock: fix unchecked error when stream channel is closed by @lucaronca in #998
• llms: add fake package by @devalexandre in #935
• examples: update pgvector README to use compose v2 by @elnoro in #969
• llms/mistral: add support for default WithTools implementation by @douglarek in #970
• vectorstores: add mongovector by @prestonvasquez in #1005
• lint: fix settings and refactor package by @tmc in #1018
• vectorstores: fix cosine similarity score calculation by @avi3tal in #1048
• internal: fix data races by @nktks in #1080
• tools: add perplexity AI by @sklinkert in #1061
• vectorstores/weaviate,pinecone: do not return error when zero documents are retrieved by @mdelapenya in #1077
• examples: add OpenAI json structured example by @lifejwang11 in #1098
• textsplitter: add optional lenFunc to MarkdownTextSplitter by @pedramr in #1096
• llms/mistral: implement embeddings.EmbedderClient for Mistral and add PGVector example by @mathiasb in #1086
• vectorstores/weaviate: fix client creator by @taigrr in #1109
• examples: add image and text content example for openai by @lifejwang11 in #1099
• test: containerize mongovector tests by @prestonvasquez in #1025
• deps: update mistral go version by @fstau in #1102
• deps: upgrade to mongo-go-driver v2.0.0 by @prestonvasquez in #1087
• docs: update Discord invite link in README by @danielmerja in #1118
• docs: add mongovector README and example by @prestonvasquez in #1063
• llms/deepseek: add ReasoningContent field for reasoner model by @semioz in #1121
• docs: fix documentation publishing by @FluffyKebab in #1123
• docs: fix artifact upload in documentation publishing by @FluffyKebab in #1124

New Contributors

• @iocron made their first contribution in #926
• @Alan796 made their first contribution in #976
• @chxru made their first contribution in #972
• @amitaifrey made their first contribution in #978
• @mheck136 made their first contribution in #984
• @takeyamakenta made their first contribution in #986
• @acrmp made their first contribution in #1003
• @anuraaga made their first contribution in #997
• @treywelsh made their first contribution in #1009
• @lucaronca made their first contribution in #998
• @prestonvasquez made their first contribution in #1005
• @avi3tal made their first contribution in #1048
• @nktks made their first contribution in #1080
• @lifejwang11 made their first contribution in #1098
• @pedramr made their first contribution in #1096
• @mathiasb made their first contribution in #1086
• @taigrr made their first contribution in #1109
• @fstau made their first contribution in #1102
• @danielmerja made their first contribution in #1118

Full Changelog: v0.1.12...v0.1.13

v0.1.13-pre.1

What's Changed

• googleai: add support for system instructions in vertex too by @eliben in #930
• googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in #936
• googleai: update dependency version by @eliben in #939
• anthropic: add support for beta header by @tmc in #967
• anthropic: add improved handling of other error event types by @tmc in #1012
• openai: reflect max_token field deprecation by @tmc in #1013
• openai: add completion_tokens_details to usage response by @tmc in #1014
• openai: add reasoning tokens to usage response by @tmc in #1015
• openai: add reasoning tokens to streaming response by @tmc in #1016
• examples: add openai o1-preview example by @tmc in #1017
• examples: improve o1 readme by @tmc in #1020
• examples: update to v0.1.13-pre.0 by @tmc in #1021
• llms: fix unkeyed fields in GenerateFromSinglePrompt struct by @iocron in #926
• ci: upgrade golangci lint version by @wangjiancn in #928
• examples: add perplexity completion example by @sklinkert in #977
• agents: optimize the mrkl prompt by @Alan796 in #976
• docs: fix Type method missing from OutputParser by @chxru in #972
• outputparser: improve BooleanOutputParser by @amitaifrey in #978
• outputparser: improve DefinedOutputParser by @amitaifrey in #980
• textsplitter: add option to join table rows by @corani in #981
• googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in #984
• openai: add support for sending structured output request for chat completions api by @takeyamakenta in #986
• redisvector: fix score threshold option by @acrmp in #1003
• milvus: add skipFlushOnWrite option by @fatedier in #992
• outputparser: use strings.Cut in structured parser by @anuraaga in #997
• examples: replace deprecated agents.Initialize by @treywelsh in #1009
• bedrock: fix unchecked error when stream channel is closed by @lucaronca in #998
• llms: add fake package by @devalexandre in #935
• examples: update pgvector README to use compose v2 by @elnoro in #969
• llms/mistral: add support for default WithTools implementation by @douglarek in #970
• vectorstores: add mongovector by @prestonvasquez in #1005
• lint: fix settings and refactor package by @tmc in #1018
• vectorstores: fix cosine similarity score calculation by @avi3tal in #1048
• internal: fix data races by @nktks in #1080
• tools: add perplexity AI by @sklinkert in #1061
• vectorstores/weaviate,pinecone: do not return error when zero documents are retrieved by @mdelapenya in #1077
• examples: add OpenAI json structured example by @lifejwang11 in #1098
• textsplitter: add optional lenFunc to MarkdownTextSplitter by @pedramr in #1096
• llms/mistral: implement embeddings.EmbedderClient for Mistral and add PGVector example by @mathiasb in #1086
• vectorstores/weaviate: fix client creator by @taigrr in #1109
• examples: add image and text content example for openai by @lifejwang11 in #1099
• test: containerize mongovector tests by @prestonvasquez in #1025
• deps: update mistral go version by @fstau in #1102
• deps: upgrade to mongo-go-driver v2.0.0 by @prestonvasquez in #1087
• docs: update Discord invite link in README by @danielmerja in #1118
• docs: add mongovector README and example by @prestonvasquez in #1063
• llms/deepseek: add ReasoningContent field for reasoner model by @semioz in #1121
• docs: fix documentation publishing by @FluffyKebab in #1123
• docs: fix artifact upload in documentation publishing by @FluffyKebab in #1124

New Contributors

• @iocron made their first contribution in #926
• @Alan796 made their first contribution in #976
• @chxru made their first contribution in #972
• @amitaifrey made their first contribution in #978
• @mheck136 made their first contribution in #984
• @takeyamakenta made their first contribution in #986
• @acrmp made their first contribution in #1003
• @anuraaga made their first contribution in #997
• @treywelsh made their first contribution in #1009
• @lucaronca made their first contribution in #998
• @prestonvasquez made their first contribution in #1005
• @avi3tal made their first contribution in #1048
• @nktks made their first contribution in #1080
• @lifejwang11 made their first contribution in #1098
• @pedramr made their first contribution in #1096
• @mathiasb made their first contribution in #1086
• @taigrr made their first contribution in #1109
• @fstau made their first contribution in #1102
• @danielmerja made their first contribution in #1118

Full Changelog: v0.1.12...v0.1.13-pre.1

v0.1.13-pre.0

What's Changed

• googleai: add support for system instructions in vertex too by @eliben in #930
• googleai: refactor shared test a bit and make it more resilient to model randomness by @eliben in #936
• googleai: update dependency version by @eliben in #939
• anthropic: Add support for beta header by @tmc in #967
• anthropic: Add improved handling of other error event types by @tmc in #1012
• openai: reflect max_token field deprecation by @tmc in #1013
• openai: add completion_tokens_details to usage response by @tmc in #1014
• openai: add reasoning tokens to usage response by @tmc in #1015
• openai: add reasoning tokens to streaming response by @tmc in #1016
• examples: Add openai o1-preview example by @tmc in #1017
• llms: GenerateFromSinglePrompt struct literal uses unkeyed fields by @iocron in #926
• ci: upgrade golangci lint version by @wangjiancn in #928
• Add perplexity completion example by @sklinkert in #977
• agents: optimize the mrkl prompt by @Alan796 in #976
• fix(docs): Type method missing from OutputParser by @chxru in #972
• outputparser: improve BooleanOutputParser by @amitaifrey in #978
• outputparser: improve DefinedOutputParser by @amitaifrey in #980
• textsplitter: add option to join table rows by @corani in #981
• googleai: add support for JSONMode and ResponseMIMEType by @mheck136 in #984
• openai: add support for sending Structured Output request for chat completions api by @takeyamakenta in #986
• redisvector: fix score threshold option by @acrmp in #1003
• milvus: add skipFlushOnWrite option by @fatedier in #992
• outputparser: use strings.Cut in structured parser by @anuraaga in #997
• examples: replace deprecated agents.Initialize by @treywelsh in #1009
• bedrock: Fix unchecked error when stream channel is closed by @lucaronca in #998
• llms: Add fake package by @devalexandre in #935
• examples: replaced compose v1 with compose v2 in readme for pgvector example by @elnoro in #969
• fix(mistral): supports the default llms.WithTools implementation by @douglarek in #970
• vectorstores: add mongovector by @prestonvasquez in #1005
• lint: fixup lint settings, refactor package by @tmc in #1018

New Contributors

• @iocron made their first contribution in #926
• @Alan796 made their first contribution in #976
• @chxru made their first contribution in #972
• @amitaifrey made their first contribution in #978
• @mheck136 made their first contribution in #984
• @takeyamakenta made their first contribution in #986
• @acrmp made their first contribution in #1003
• @anuraaga made their first contribution in #997
• @treywelsh made their first contribution in #1009
• @lucaronca made their first contribution in #998
• @prestonvasquez made their first contribution in #1005

Full Changelog: v0.1.12...v0.1.13-pre.0

v0.1.12

What's Changed

• llms/googleai: fix vertex do not return usage info by @wangjiancn in #904
• bugfix: Anthropic Function Calling by @lwlee2608 in #899
• llms/anthropic: Fix Content set incorrectly for anthropic llm requests by @JckHoe in #908
• llms/googleai: fix convert tool error by @wangjiancn in #903
• llms/googleai: Fix usage population tests, max token test, update dpep by @tmc in #910
• docs/groq: by @devalexandre in #907
• llms/watsonx: update module by @h0rv in #902
• docs: fix text_splitters mdx code example never closed by @4lxprime in #900
• textsplitter: add WithHeadingHierarchy option to markdown splitter to retain heading hierarchy in chunks by @iwilltry42 in #898
• examples: point watsonx example at current main by @tmc in #911
• outputparser: add Defined parser to extract a struct from LLM output by @erictse in #856
• anthropic: Improve streaming message handling in anthropic client by @tmc in #912
• googleai: Settle on GOOGLE_API_KEY for google auth env var name by @tmc in #913
• llms: Increase default tokens by @tmc in #914
• examples: Add example readmes by @tmc in #916
• examples: Improve top level readme by @tmc in #919
• anthropic: Spruce up tool calling example by @tmc in #921
• examples: point to 0.1.12-pre.0 by @tmc in #922

New Contributors

• @JckHoe made their first contribution in #908
• @4lxprime made their first contribution in #900
• @iwilltry42 made their first contribution in #898
• @erictse made their first contribution in #856

Full Changelog: v0.1.11...v0.1.12

v0.1.11

What's Changed

• llms: add watsonx by @h0rv in #577
• pgvector restore WithConnectionURL option by @tmc in #832
• examples: Update to v0.1.10 by @tmc in #833
• agents: GetTools added to Agent interface by @AugustDev in #831
• examples: add redis vectorstore example by @CrazyWr in #834
• llms/googleai: batch embedding calls by @johanbrandhorst in #825
• fix: better handling of errors in openai-like streaming messages by @douglarek in #839
• llms/googleai: upgrade genai SDKs and fix build issue vs. new version by @eliben in #854
• fix: handle nil pointer exception in chat_prompt_template by @ankitraj2330 in #879
• httputil: debug transport layer by @AugustDev in #845
• llms: Add improved yaml and json marshaling by @tmc in #880
• tools: Improve tool choice population and parsing by @tmc in #883
• memory: move mongo chat history into the separate module by @CrazyWr in #843
• llms: Tidy up marshaling by @tmc in #884
• anthropic: Add tool/function calling support by @lwlee2608 in #882
• milvus_vectorstore: store metadata with JSON data type & support search with filter by @CrazyWr in #844
• readme: add scheme to vectorstores/chroma URL by @codefromthecrypt in #846
• llms: Fix ErrIncompleteEmbeddings Message Typos by @wgeorgecook in #872
• googleai: add support for array type in convertToolSchemaType by @johnknott in #865
• marita: update Authorization by @devalexandre in #864
• Fix typos map key value of the modelToContextSize by @zhanluxianshen in #874
• memory: Add Zep Cloud integration by @paul-paliychuk in #746
• openai: add the field detail in ImageURLContent struct by @douglarek in #853
• weaviate: Fix up weaviate tests by @tmc in #885
• deps: clean up direct dep on zerolog by @tmc in #886
• googleai: Fix: Resolve Type Error in googleai convertTools by @wangjiancn in #888
• openai: enable optional return of usage data while streaming by @wangjiancn in #887
• llms/googleai: Support more option.ClientOption and update google ai sdk by @wangjiancn in #841
• googleai: Remove unused err, fix typo by @tmc in #891
• examples: Correct API key usage for Groq integration by @Ashad001 in #893
• ollama: Fix JSON format bug issue when not streaming by @doslindos in #892

New Contributors

• @h0rv made their first contribution in #577
• @johanbrandhorst made their first contribution in #825
• @ankitraj2330 made their first contribution in #879
• @lwlee2608 made their first contribution in #882
• @codefromthecrypt made their first contribution in #846
• @wgeorgecook made their first contribution in #872
• @johnknott made their first contribution in #865
• @zhanluxianshen made their first contribution in #874
• @paul-paliychuk made their first contribution in #746
• @wangjiancn made their first contribution in #888
• @Ashad001 made their first contribution in #893
• @doslindos made their first contribution in #892

Full Changelog: v0.1.10...v0.1.11-pre.0