Bump langchainrb from 0.15.2 to 0.19.0

[dependabot]

Bumps langchainrb from 0.15.2 to 0.19.0.

Release notes

Sourced from langchainrb's releases.

0.19.0

What's Changed

• Anthropic Tools: added default input_schema if no params by @​dghirardo in patterns-ai-core/langchainrb#837
• Fix issue with clearing instructions by @​qarol in patterns-ai-core/langchainrb#836
• Allow setting safety_setting: [] in default_options for Langchain::LLM::GoogleGemini and Langchain::LLM::GoogleVertexAI constructors by @​andreibondarev in patterns-ai-core/langchainrb#838
• Enhance code comments by @​andreibondarev in patterns-ai-core/langchainrb#846
• Fix MistralAIMessage to handle "Tool" Output by @​dkaplan88 in patterns-ai-core/langchainrb#850
• Shorter model name params by @​bborn in patterns-ai-core/langchainrb#840
• 0.19.0 by @​andreibondarev in patterns-ai-core/langchainrb#854

New Contributors

• @​qarol made their first contribution in patterns-ai-core/langchainrb#836
• @​dkaplan88 made their first contribution in patterns-ai-core/langchainrb#850

Full Changelog: patterns-ai-core/langchainrb@0.18.0...0.19.0

0.18.0

What's Changed

• Bump anthropic gem by @​andreibondarev in patterns-ai-core/langchainrb#819
• Add streaming support for Anthropic by @​chalmagean in patterns-ai-core/langchainrb#809
• Resolve the issue of the AWS Bedrock chat model always returning nil by @​khaile in patterns-ai-core/langchainrb#801
• Fix zeitwerk error when eager_load is turned on by @​andreibondarev in patterns-ai-core/langchainrb#822
• Refactor assistant determine tool role method by @​andreibondarev in patterns-ai-core/langchainrb#823
• Introduce support_system_message? method by @​andreibondarev in patterns-ai-core/langchainrb#824
• Introduce Langchain::Assistant#parallel_tool_calls options whether to allow the LLM to make multiple parallel tool calls by @​andreibondarev in patterns-ai-core/langchainrb#827
• 0.18.0 by @​andreibondarev in patterns-ai-core/langchainrb#828

Full Changelog: patterns-ai-core/langchainrb@0.17.1...0.18.0

0.17.1

What's Changed

• Move adapter-related classes to separate files by @​khaile in patterns-ai-core/langchainrb#807
• Fix Langchain::Tool::Database#describe_table method by @​andreibondarev in patterns-ai-core/langchainrb#814
• 0.17.1 by @​andreibondarev in patterns-ai-core/langchainrb#815

Full Changelog: patterns-ai-core/langchainrb@0.17.0...0.17.1

0.17.0

What's Changed

• Bump webrick from 1.8.1 to 1.8.2 by @​dependabot in patterns-ai-core/langchainrb#797
• Langchain::Assistant when using OpenAI accepts a message with image_url by @​andreibondarev in patterns-ai-core/langchainrb#799
• Langchain::Assistant when using MistralAI accepts a message with image_url by @​andreibondarev in patterns-ai-core/langchainrb#803
• Vectorsearch providers should utilize the global Langchain.logger by @​andreibondarev in patterns-ai-core/langchainrb#804
• Remove Langchain::LLM::GooglePalm by @​andreibondarev in patterns-ai-core/langchainrb#805
• 0.17.0 by @​andreibondarev in patterns-ai-core/langchainrb#806

Full Changelog: patterns-ai-core/langchainrb@0.16.1...0.17.0

... (truncated)

Changelog

Sourced from langchainrb's changelog.

[0.19.0] - 2024-10-23

• [BREAKING] [https://redirect.github.com/Shorter model name params patterns-ai-core/langchainrb#840] Rename chat_completion_model_name parameter to chat_model in Langchain::LLM parameters.
• [BREAKING] [https://redirect.github.com/Shorter model name params patterns-ai-core/langchainrb#840] Rename completion_model_name parameter to completion_model in Langchain::LLM parameters.
• [BREAKING] [https://redirect.github.com/Shorter model name params patterns-ai-core/langchainrb#840] Rename embeddings_model_name parameter to embedding_model in Langchain::LLM parameters.
• [BUGFIX] [https://redirect.github.com/Fix MistralAIMessage to handle "Tool" Output  patterns-ai-core/langchainrb#850/] Fix MistralAIMessage to handle "Tool" Output
• [BUGFIX] [https://redirect.github.com/Anthropic Tools: added default input_schema if no params patterns-ai-core/langchainrb#837] Fix bug when tool functions with no input variables are used with Langchain::LLM::Anthropic
• [BUGFIX] [https://redirect.github.com/Fix issue with clearing instructions patterns-ai-core/langchainrb#836] Fix bug when assistant.instructions = nil did not remove the system message
• [FEATURE] [https://redirect.github.com/Allow setting safety_setting: [] in default_options for Langchain::LLM::GoogleGemini and Langchain::LLM::GoogleVertexAI constructors patterns-ai-core/langchainrb#838] Allow setting safety_settings: [] in default_options for Langchain::LLM::GoogleGemini and Langchain::LLM::GoogleVertexAI constructors

[0.18.0] - 2024-10-12

• [BREAKING] Remove Langchain::Assistant#clear_thread! method
• [BREAKING] Langchain::Messages::* namespace had migrated to Langchain::Assistant::Messages::*
• [BREAKING] Modify Langchain::LLM::AwsBedrock constructor to pass model options via default_options: {...}
• Introduce Langchain::Assistant#parallel_tool_calls options whether to allow the LLM to make multiple parallel tool calls. Default: true
• Minor improvements to the Langchain::Assistant class
• Added support for streaming with Anthropic
• Bump anthropic gem
• Default Langchain::LLM::Anthropic chat model is "claude-3-5-sonnet-20240620" now

[0.17.1] - 2024-10-07

• Move Langchain::Assistant::LLM::Adapter-related classes to separate files
• Fix Langchain::Tool::Database#describe_table method

[0.17.0] - 2024-10-02

• [BREAKING] Langchain::Vectorsearch::Milvus was rewritten to work with newer milvus 0.10.0 gem
• [BREAKING] Removing Langchain::LLM::GooglePalm
• Assistant can now process image_urls in the messages (currently only for OpenAI and Mistral AI)
• Vectorsearch providers utilize the global Langchain.logger
• Update required milvus, qdrant and weaviate versions

[0.16.1] - 2024-09-30

• Deprecate Langchain::LLM::GooglePalm
• Allow setting response_object: {} parameter when initializing supported Langchain::LLM::* classes
• Simplify and consolidate logging for some of the LLM providers (namely OpenAI and Google). Now most of the HTTP requests are being logged when on DEBUG level
• Improve doc on how to set up a custom logger with a custom destination

[0.16.0] - 2024-09-19

• Remove Langchain::Thread class as it was not needed.
• Support cohere provider for Langchain::LLM::AwsBedrock#embed

[0.15.6] - 2024-09-16

• Throw an error when Langchain::Assistant#add_message_callback is not a callable proc.
• Resetting instructions on Langchain::Assistant with Google Gemini no longer throws an error.
• Add Meta models support for AWS Bedrock LLM

[0.15.5] - 2024-09-10 🇧🇦

• Fix for Langchain::Prompt::PromptTemplate supporting nested JSON data
• Require common libs at top-level
• Add add_message_callback to Langchain::Assistant constructor to invoke an optional function when any message is added to the conversation
• Adding Assistant syntactic sugar with #run! and #add_message_and_run!

... (truncated)

Commits

• f980820 0.19.0 (#854)
• cf2bafd Shorter model name params (#840)
• 8091e54 Update CHANGELOG.md
• fd7e02e Fix MistralAIMessage to handle "Tool" Output (#850)
• 9e93084 Enhance code comments (#846)
• 630428f Update README.md
• 7ce8ed5 Update CHANGELOG.md
• 69a47c7 Allow setting safety_setting: [] in default_options for Langchain::LLM::Googl...
• d127ced Update dependabot.yml
• 3a8ebcc Fix issue with clearing instructions (#836)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)