This pull request adds a new feature to the flow editor that allows
users to easily import example flows from the
[logspace-ai/langflow_examples](https://github.com/logspace-ai/langflow_examples)
repository on GitHub. The feature is accessible via the import example
button
Clicking on the "Import Examples" button opens a dialog box that
displays a list of available example flows from the GitHub repository.
Users can select one example to import, and the flow editor will
automatically add the selected flow to the user's current project.
This feature saves users time and effort by providing a convenient way
to explore and utilize pre-built flows.
Additionally, this feature promotes collaboration and community
involvement by encouraging users to contribute their own flows to the
repository for others to use and benefit from.
This change adds error handling to catch a specific exception that may occur when processing documents with the ChromaDB library. If there are not enough documents for indexing, the error message will suggest reducing the chunk size in TextSplitter.
Add a new file `callback.py` that contains a new class `StreamingLLMCallbackHandler` that inherits from `AsyncCallbackHandler`. This class handles streaming LLM responses. It has a constructor that takes a `websocket` parameter and sets it as an instance variable. It also has an `on_llm_new_token` method that takes a `token` parameter and sends a `ChatResponse` object to the `websocket` instance variable.
Update `chat_manager.py` to import the new `StreamingLLMCallbackHandler` class. Add a new function `try_setting_streaming_options` that takes a `langchain_object` and a `websocket` parameter. This function checks if the `llm` attribute of the `langchain_object` is an instance of `OpenAI`, `ChatOpenAI`, `AzureOpenAI`, or `AzureChatOpenAI`. If it is, it sets the
"UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 9465: character maps to
<undefined>".
Specifying the encodint type in the function helps to fix that error.
fix(schemas.py): add validation for file response type and data type
test(test_websocket.py): remove data and data_type fields from ChatResponse messages in tests
feat(cache): add support for multiple clients and context manager to set client_id
feat(cache): add observer pattern to notify on cache changes
feat(cache): add async observer pattern to notify on cache changes in async functions
feat(cache): add methods to add pandas DataFrame or Series and PIL Image to cache
feat(cache): add method to get an object from cache by key
feat(cache): add method to get the last added item in cache
feat(chat.py, chat_manager.py): add error handling for async_get_result_and_steps
feat(chat.py): add client_id to websocket endpoint
feat(schemas.py): add data_type field to ChatResponse schema
refactor(run.py): memoize build_langchain_object_with_caching function with maxsize of 10
Add an advanced flag to the TemplateFieldCreator and FrontendNode classes to allow for fields to be hidden from the user interface. In the TemplateFieldCreator class, the advanced flag is set to False by default. In the FrontendNode class, the advanced flag is set to False for all fields except for "model_type" and "model_kwargs", which are set to True.
feat(cache): add support for pandas and PIL Image objects caching
fix(interface): import cache-related functions from base.py module
test(cache): update import statements in cache-related test file
refactor(tools/base.py): comment out unused code for ToolCreator
feat(nodes.py): add 'return_direct' field to ToolNode template and set base class to 'Tool'
