There is a recurring intermittent bug, where Chains fail to validate, with an error "Required module ____ for module ____ not found". This happens frequently for all LLMs that inherit from the LLM class (example Cohere's wrapper).
This is caused by this chunk of code.
This also explains why the bug is intermittent and not every time.
"in" is matching LLM from source_types with BaseLLM from target_reqs. Also, this doesn't need to be a nested loop, it can be done with one loop.
I'm a user of LangFlow, and a first time contributor. Thanks!
The package version has been updated to 0.2.2 to reflect the changes made to the package. This is a chore commit as it does not include any functional changes to the package.
The `AgentType` enum is added to the `langchain.agents.custom` module to improve readability and type safety. The `InitializeAgent` class now uses the `AgentType` enum to ensure that the `agent` parameter is a valid value from the enum.
🔼 chore(pyproject.toml): bump package version to 0.2.1
The langchain dependency has been updated to version 0.0.215, which includes bug fixes and performance improvements. The package version has been bumped to 0.2.1 to reflect the changes made.
The import statement for the MidjourneyIcon was misspelled as MidjorneyIcon, which caused a runtime error. This commit fixes the typo by changing the import statement to MidjourneyIcon.
The import of Boxes and LayoutDashboard were removed as they were not being used in the file. New icons were added to nodeIconsLucide to improve the variety of icons available for use. The new icons added are MongoDBAtlasVectorSearch, Pinecone, and SupabaseVectorStore.
🔥 chore(utils.ts): remove unused import of Boxes and LayoutDashboard
The `update_settings` function now accepts a `cache` parameter that allows the user to specify the type of cache to use. The `cache` parameter is set to a default value of `SQLiteCache` and can be overridden by setting the `LANGCHAIN_CACHE` environment variable. This feature improves the flexibility of the application as it allows the user to choose the type of cache that best suits their needs.
The cache configuration option has been added to the settings file with a default value of "InMemoryCache". This allows the user to choose the cache implementation they want to use.
This commit adds support for configurable LLM caching. The `setup_llm_caching` function now imports the cache class from the `langchain.cache` module based on the `settings.cache` value. If the import is successful, the `langchain.llm_cache` is set to an instance of the cache class. If the import fails, a warning is logged. If an exception is raised during the setup, a warning is logged with the error message.
✨ feat(main.py): call setup_llm_caching function on app startup
The `setup_llm_caching` function is added to `utils.py` to set up LLM
caching. The function is then called on app startup in `main.py` using
the `app.on_event("startup")` method. This improves the performance of
the application by caching LLM objects.
✨ feat(main.py): call setup_llm_caching function on app startup
The `setup_llm_caching` function is added to `utils.py` to set up LLM caching. The function is then called on app startup in `main.py` using the `app.on_event("startup")` method. This improves the performance of the application by caching LLM objects.
The version number has been updated from 0.1.7 to 0.2.0 to reflect the changes made to the package. This is a chore commit as it does not add any new features or fix any bugs, but rather updates the version number.
🎨 style(GenericNode): change nodeIcons import to nodeIconsLucide to
match the new icon library
🎨 style(NodeModal): change Icon type to any to fix type error
🎨 style(chatInput): remove unnecessary array brackets
🎨 style(DisclosureComponent): change Icon size to 22 to match the new
icon library
🎨 style(extraSidebarComponent): change nodeIcons import to
nodeIconsLucide to match the new icon library and add Search icon
🎨 style(components/index): add SVGProps to import and change Icon type
to any to fix type error
✨ feat(utils.ts): add support for Lucide icons to be used in the app to
improve UI and UX.
feat(tabsContext.tsx): add support for display_name property in node templates to allow custom node names
fix(tabsContext.tsx): add null checks to prevent errors when processing flow edges and nodes
refactor(typesContext/index.ts): change template object type to APIClassType to match usage in tabsContext
The SlackDirectoryLoader is added to the list of document loaders in the DocumentLoaderFrontNode class. This allows users to load zip files from Slack into the application.
feat(frontend): add save function to TabsContext to enable saving of changes made to tabs
fix(frontend): add save function to TabsContext in ParameterComponent to enable saving of changes made to tabs
This commit updates the langchain dependency from version 0.0.209 to version 0.0.211. This is a minor version update that includes bug fixes and performance improvements.
The GitLoader template now has four new fields: repo_path, clone_url, branch, and file_filter. These fields allow the user to specify the repository path, clone URL, branch, and file extensions to be loaded. This improves the flexibility of the GitLoader template and allows it to be used in a wider range of scenarios. Additionally, a minor change was made to the add_extra_fields method to ensure that the field.show attribute is set to True for all fields.
The `instantiate_documentloader` function now supports filtering files by extension using a `file_filter` parameter. The parameter is a string of comma-separated extensions, and the function now converts it into a lambda function that filters files based on whether their name contains any of the specified extensions. This improves the flexibility of the document loader by allowing it to load only specific types of files.
