🔨 refactor(parameterComponent): remove unused imports and refactor onChange function to handleOnNewValue
✨ feat(tabsContext): add tabsState and setTabsState to TabsContextType and TabsProvider
🔨 refactor(flowSettingsModal): refactor handleSaveFlow function to update flow and setTabsState with isPending false
The update_flow endpoint now returns a FlowRead response model instead of FlowReadWithStyle. The parameterComponent file has been refactored to remove unused imports and to use a handleOnNewValue function to handle onChange events. The TabsContextType and TabsProvider have been updated to include tabsState and setTabsState. The flowSettingsModal has been refactored to update the flow and setTabsState with isPending false.
🔨 refactor(extraSidebarComponent): add tabsState and setTabsState to TabsContextType
🐛 fix(extraSidebarComponent): disable save button when flow is not pending
🐛 fix(extraSidebarComponent): update flow state after saving
The TabsContextType now includes tabsState and setTabsState to allow for the management of the state of each tab. The save button is now disabled when the flow is not pending. The flow state is now updated after saving to reflect the changes made.
The description of CombineDocsChainNode was updated to reflect the actual functionality of the node. The node is now used to load a question answering chain instead of constructing a chain from combined documents.
The openai_api_version field value is no longer set as it is not needed. The password field is now set to False for fields not containing 'key' or 'token' in their name to improve security.
🐛 fix(llms.py): remove setting of openai_api_version field value
🔧 chore(base.py): fix typo in docstring
The fix in chat.py ensures that an error message is yielded when an exception occurs during stream_build. This helps to provide more information to the client-side when an error occurs. The typo in base.py's docstring is fixed to improve readability.
- Rename `VectorStoreAgent` to `Vector store agent` in `custom.py`
- Replace "Construct a sql agent from an LLM and tools." with "Construct an SQL agent from an LLM and tools." in `custom.py`
- Update descriptions of `SQLAgentNode`, `TimeTravelGuideChainNode`, `CombineDocsChainNode`, and `ToolNode` in related files
- Increase width of `ExtraSidebarComponent` container in `index.tsx` from 52 to 56
The build_template function is now outside of the DocumentLoaderFrontNode class to improve code organization and make it more modular. This change also makes it easier to reuse the function in other parts of the codebase.
Added new OpenAI chat models to the CHAT_OPENAI_MODELS list to improve the quality of the chatbot responses. The new models are "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-4-0613", and "gpt-4-32k-0613". The existing models "gpt-3.5-turbo" and "gpt-4-32k" were also updated to their latest versions.
The status codes have been added to the API endpoints to improve the readability of the code and to make it more explicit what the expected response codes are. The status codes have been added to the following endpoints: create_flow, read_flows, read_flow, update_flow, delete_flow, create_flows, upload_file, and download_file.
✨ feat(endpoints.py): add flow_id parameter to predict_flow function to allow for running a flow by ID
The predict_flow function now includes a flow_id parameter and a session dependency to allow for running a flow by ID. The flow object is retrieved from the session using the flow_id parameter. If the flow is not found, a ValueError is raised.
🔨 refactor(constants.tsx): change API_URL constant to BASE_API_URL and add flow_id parameter to run_flow function
The API_URL constant has been renamed to BASE_API_URL to better reflect its purpose. The run_flow function now includes a flow_id parameter to allow for running a flow by ID. The flow_id parameter is used to construct the API URL.
The code now handles exceptions that may occur while building the flow. A final response is added to the event stream to indicate the end of the stream.
The try-except block was added to handle exceptions that may occur in the init_build function. If an exception occurs, it is logged and an HTTPException with a status code of 500 is returned. This ensures that the server does not crash and provides a more informative error message to the client.
The init_build endpoint now returns a status code of 201 to indicate that a new resource has been created. This improves the consistency of the API and makes it easier for clients to understand the response.
🚀 feat(chat.py): add response models to /build/init and /build/{flow_id}/status endpoints
The InitResponse and BuiltResponse models are now imported from the schemas module to improve code organization. The /build/init and /build/{flow_id}/status endpoints now have response models to provide a clear understanding of the expected response.
The process_tweaks function has been refactored to improve readability and maintainability. The function now takes in two parameters, graph_data and tweaks, and returns the modified graph_data. The tweaks parameter is a dictionary of dictionaries, where the key is the node id and the value is a dictionary of the tweaks. The function processes the graph data to add the tweaks by iterating over the nodes and checking if the node id is in the tweaks dictionary. If it is, the function applies the tweaks to the node by updating the template data with the new values. The function also prints a message to the console to indicate that a tweak has been applied.
The PredictRequest schema now includes an optional tweaks field, which is a dictionary of dictionaries. This field allows for additional customization of the prediction request, such as specifying tool names or descriptions. The tweaks field is optional, and if not provided, the default value is an empty dictionary. The schema_extra attribute has also been updated to include an example of the new tweaks field.
🐛 fix(endpoints.py): change predict endpoint to use Flow object instead of flow_id
🐛 fix(endpoints.py): add support for processing tweaks in predict endpoint
The predict endpoint now requires authentication using HTTPBearer. The flow_id is now extracted from the bearer token instead of being passed as a parameter. This improves security as the flow_id is not exposed in the URL. The predict endpoint now uses the Flow object instead of the flow_id to retrieve the graph data. This improves code readability and reduces the number of database queries. The predict endpoint now supports processing tweaks, which allows for more flexibility in the processing of messages.
The function stream_build was returning a JSONResponse with an error message when an exception was raised. This is not the correct way to handle errors in FastAPI. Instead, we should raise an HTTPException with the appropriate status code and error message.
The unused imports and exception handling for WebSocketDisconnect and WebSocketException were removed from the chat.py file. The code was reformatted to improve readability.
🔥 refactor(chat.py): remove unused imports and exception handling
✨ feat(chat.py): add build_status endpoint to check if flow_id is in flow_data_store
The function name websocket_endpoint was renamed to chat to improve semantics. The new build_status endpoint was added to check if a flow_id is in the flow_data_store. This endpoint returns a JSON response with a boolean value indicating whether the flow_id is built or not. If the flow_id is not in the flow_data_store, a JSON response with a value of False is returned. If an exception occurs, a 500 HTTPException is raised with the exception message as the detail.
The build method call in the for loop of the build_vertices method is unnecessary as the vertices are already sorted and built in the topological_sort method. The yield from statement is used to return the sorted vertices.
The changes in this commit handle exceptions that may occur when creating a streaming response. The try-except block ensures that any exceptions are caught and an appropriate response is returned. Additionally, the SSE response has been improved by adding a valid flag and node id to the response. This provides more information to the client about the status of the node build and allows for better error handling.
🐛 fix(chat.py): handle exceptions when creating a streaming response
The commented out code for the /build/{client_id} endpoint has been removed as it is no longer needed. The new implementation uses the /build/init endpoint to initiate the build process and then establishes an SSE connection using EventSource to stream the build process. This allows for a more efficient and responsive build process as the client can receive updates in real-time.
🔥 chore(chat.py, index.tsx): remove commented out code for /build/{client_id} endpoint
✨ feat(chat.py): add support for storing graph data and returning a unique session ID for building langchain object
✨ feat(chat.py): add support for streaming the build process based on stored flow data
The fix adds a check for the client_id in the in_memory_cache before handling the websocket. This ensures that the flow has been built before sending messages.
The first feature adds support for storing graph data and returning a unique session ID for building the langchain object. This allows the user to build the flow and then send messages.
The second feature adds support for streaming the build process based on stored flow data. This allows the user to see the progress of the build process.
The return type of the generator_build method has been changed from List[Vertex] to Generator to improve the semantics of the method. The method now yields each vertex in the graph instead of returning a list of vertices.
🔥 refactor(utils.py): remove unused imports and dependencies
The changes remove unused imports and dependencies from the codebase, which improves the code's readability and maintainability.
🐛 fix(chat.py): fix generator_build method to yield node_repr and node_id
✨ feat(chat.py): add valid and id fields to error response to improve error handling
🔧 refactor(manager.py): change logger.exception to logger.error to log exceptions
🔧 refactor(graph/base.py): add logging to generator_build method to improve debugging
🔧 refactor(vertex/base.py): rename cache.base to cache.utils to improve semantics
The post_build method in chat.py was renamed to stream_build to better reflect its functionality. The generator_build method in graph/base.py was fixed to yield node_repr and node_id instead of node._built_object_repr() and node.id. The error response in chat.py now includes valid and id fields to improve error handling. logger.exception in manager.py was changed to logger.error to log exceptions. The generator_build method in graph/base.py now logs the sorted vertices to improve debugging. The cache.base module in vertex/base.py was renamed to cache.utils to better reflect its functionality.
✨ feat(chat.py): add SSE support to post_build endpoint to stream build progress to the client
The post_build endpoint now returns a StreamingResponse object that streams Server-Sent Events (SSE) to the client. This allows the client to receive build progress updates in real-time. The event_stream function is responsible for generating the SSE events and is called by the StreamingResponse object. The SSE events contain information about the build progress, including whether the build was successful or not, the parameters used to build each node, and the node ID. The chat_manager.set_cache method is called to cache the built graph object.
🔥 refactor(manager.py): remove unused build method and rename set_cache to set_client_cache
🚀 chore(manager.py): add async keyword to close_connection method
The close_connection method now accepts an integer as the status parameter instead of a status enum. The build method was removed as it was not being used. The set_cache method was renamed to set_client_cache to improve semantics. The close_connection method was updated to be an async method.
🚀 feat(base.py): add generator_build method to build each node in the graph and yield it
The topological_sort method performs a topological sort of the vertices in the graph, returning a list of vertices in topological order. The generator_build method builds each node in the graph and yields it. These methods are useful for building the graph in a specific order, which is important for certain algorithms that rely on the order of the nodes.
🎨 refactor(run.py): update import statement for compute_dict_hash, load_cache, and memoize_dict
The import of logger in base.py was not being used, so it was removed to improve code readability. In run.py, the import statement for compute_dict_hash, load_cache, and memoize_dict was updated to reflect the new location of these functions in the cache.utils module. This improves the organization of the code and makes it easier to find the relevant functions.
✨ feat(manager.py): add build method to build langchain object and store it in an in-memory cache
The `process_message` method now checks if the langchain object has been built and stored in the in-memory cache before processing the message. If the object is not found, the connection is closed with an error message. A new `build` method has been added to build the langchain object and store it in an in-memory cache. This method is called before processing any messages.
✨ feat(cache/utils.py): add support for clearing old cache files and memoization of dictionary functions
The CACHE variable in CacheManager class has been renamed to _cache to follow naming conventions. The utils.py module now supports clearing old cache files and memoization of dictionary functions. The clear_old_cache_files function removes old cache files if the number of cache files exceeds the max_cache_size. The memoize_dict decorator memoizes dictionary functions and clears the cache when the clear_cache method is called.
This commit adds a new class InMemoryCache to implement an in-memory cache with a Least Recently Used (LRU) eviction policy. The cache supports setting a maximum size and expiration time for cached items. The cache is thread-safe using a threading Lock. The InMemoryCache class inherits from the BaseCache class and implements the get, set, get_or_set, delete, clear, __contains__, __getitem__, __setitem__, __delitem__, __len__, and __repr__ methods.
This commit refactors the BaseCache class to use abstract methods instead of concrete methods. This makes the class more flexible and allows for different implementations of the cache. The abstract methods include get, set, delete, clear, __contains__, __getitem__, __setitem__, and __delitem__.
✨ feat(cache/__init__.py): add InMemoryCache to exported modules
🔖 refactor(endpoints.py): remove unused import statement
The post_build endpoint in chat.py now has exception handling to catch any errors that may occur during the build process. InMemoryCache is now exported as part of the cache module. The endpoints.py file has been refactored to remove an unused import statement.
🐛 fix(langflow): fix version import error in version endpoint
The version endpoint is added to the API to allow clients to retrieve the version of the Langflow package. The version is obtained using the `metadata.version` function from the `importlib` module. In case the package metadata is not available, an empty string is returned. The version endpoint was previously returning an error due to an import error. The error is fixed by importing the `__version__` variable from the `langflow` module.
The `load_dotenv` function from the `dotenv` package is now used to load environment variables from a `.env` file. This allows for a more flexible configuration of the application as environment variables can be loaded from a file instead of being hardcoded in the code. The `.env` file path can be specified via the `env_file` parameter.
The graph_data variable was previously assigned to flow_obj.flow, which is incorrect as the flow_obj object does not have a flow attribute. Instead, the correct attribute to use is flow_obj.data.
🐛 fix(base.py): improve error message when invalid payload is received
The logger is added to the Graph class to improve debugging capabilities. The error message when an invalid payload is received is improved to include the keys that were found in the payload. This makes it easier to identify the issue and fix it.
The `display_name` field is added to the `FrontendNode` class to allow for a more user-friendly name to be displayed in the UI. If `display_name` is not set, the `name` field will be used instead.
