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
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
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'
feat: add logging for missing nodes in LangChainTypeCreator classes
feat: add support for custom TextLoader document loader
fix: fix typo in document loaders base module name
fix: fix typo in text_splitters package name and add __init__.py file
refactor(interface): rename textSplitters to text_splitters
refactor(interface): rename documentLoaders to document_loaders
refactor(interface): rename vectorStore to vectorstore
refactor(interface): rename toolkits to toolkit
refactor(interface): rename tools to tool
refactor(interface): rename prompts to prompt
refactor(interface): rename memories to memory
refactor(interface): rename embeddings to embedding
refactor(interface): rename wrappers to wrapper
fix(interface): fix typo in text_splitters/base.py
fix(interface): fix typo in toolkits/base.py
fix(interface): fix typo in vectorstore/base.py
fix(interface): fix typo in wrappers/base.py
feat(interface): add logging for when a type is not loaded
chore(poetry.lock): update lit version from 16.0.0 to 16.0.1
feat(poetry.lock): add nltk package with version 3.8.1 and its dependencies
chore(poetry.lock): update posthog package version to 2.5.0
chore(poetry.lock): remove torch and triton package versions
# removable and draggable edges
This pull request adds two new features: removable edges and draggable
edges. Removable edges allow users to delete unwanted connections
without using the keyboard, while draggable edges enable the
repositioning of connections
