🔧 chore(loading.py): call initialize_vertexai function when node_type is "VertexAI"
The `llm.py` file now includes a new function `initialize_vertexai` that initializes the VertexAI credentials if a `credentials` parameter is provided. This allows for the usage of VertexAI credentials in the application. In `loading.py`, the `initialize_vertexai` function is called when the `node_type` is "VertexAI", ensuring that the VertexAI credentials are properly initialized for that specific node type.
The condition for showing fields in the VertexAI class has been simplified to exclude specific field names. This improves readability and maintainability of the code.
📝 chore(llms.py): improve field configuration for VertexAI template and modify field type for "credentials"
The `add_extra_fields` method is modified to add an additional field called "credentials" for the VertexAI template. The field is of type "file" and is required. It allows the user to upload a JSON file as credentials. The `format_openai_field` method is also updated to handle the new "credentials" field.
The `instantiate_textsplitter` function has been refactored to improve readability and remove unnecessary code. The condition for creating the `text_splitter` object has been simplified and the `separator_type` parameter is now removed from the `params` dictionary if it exists. Additionally, the `language` parameter is now passed as an instance of the `Language` class from the `langchain.text_splitter` module. This change ensures that the `text_splitter` object is created correctly and the `split_documents` method is called with the appropriate parameters.
The options list for the separator_type field in the TextSplittersFrontendNode class has been extracted into a variable called options. This improves code readability and allows for easier modification and sorting of the options list.
The documentation link for ConversationBufferMemory in the memories section has been updated to point to the correct URL "https://python.langchain.com/docs/modules/memory/how_to/buffer". This change ensures that users can access the correct documentation for using ConversationBufferMemory.
🐛 fix(loading.py): handle case where separator_type is not provided in params
The first fix ensures that if the metadata is an empty dict, it will not be added to the documents if they already have metadata. This prevents overwriting existing metadata.
The second fix handles the case where the separator_type is not provided in the params. In this case, the text_splitter will be instantiated using the class_object and the params as is.
🔥 refactor(manager.py): remove unnecessary blank line at the end of the file
The package version has been updated to 0.2.3 in the pyproject.toml file. This is a chore as it does not affect the functionality of the package. The blank line at the end of the manager.py file has been removed as it is unnecessary and does not add any value to the code. This is a refactor as it improves the code readability.
The variable name static_files_dir was changed to improve semantics. It is now more clear that it is a directory path. An optional static_files_dir parameter was added to the setup_app function to allow for a directory path to be passed in. This allows for more flexibility in serving static files.
🐛 fix(__main__.py): fix static_files_dir variable name to improve semantics
The first change removes an extra blank line in the ChatManager class. The second change updates the try_setting_streaming_options function to use the ChatConfig class to set the streaming option instead of hardcoding it. This makes the code more modular and easier to maintain.
This commit adds a new function `instantiate_llm` to handle LLM (Language Model) instantiation. It also sets the `ChatConfig.streaming` attribute based on the `openai_api_base` parameter. This is a workaround to ensure that JinaChat works until streaming is implemented.
The ChatConfig class is added to the project with a single attribute, streaming, set to True. This attribute is used to determine whether the chatbot should use streaming or request-response communication with the client.
✨ feat(__main__.py, main.py): add support for a custom static files directory to be passed as an argument to the app
The `setup_static_files` function has been moved from `__main__.py` to `main.py` to improve code organization. The function has also been renamed to `setup_app` to better reflect its purpose. The `create_app` function has been renamed to `setup_app` to follow the naming convention of the new function. The `setup_app` function now accepts an optional argument `static_files_dir` which allows the user to specify a custom directory for static files. This improves the flexibility of the app as it can now be run with a custom frontend.
This commit updates the documentation in the constants.py file to include additional API options that can be used instead of the default OpenAI API. The new options are JinaChat, LocalAI, and Prem. This change provides more information to the user and allows them to make an informed decision when choosing an API to use.
The `info` field is added to the `TemplateField` class to provide additional information about the field. The `OPENAI_API_BASE_INFO` constant is added to the `constants.py` file to provide information about the base URL of the OpenAI API and how it can be changed to use other APIs like Prem and LocalAI. The `info` field is set to `OPENAI_API_BASE_INFO` for the `openai_api_base` field in the `LLMFrontendNode` class in `llms.py`.
Added documentation links for various document loaders, embeddings, and llms to improve the readability and usability of the config.yaml file. These links provide a quick reference to the documentation for each of the modules, making it easier for developers to understand and use them.
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.
The import of RecursiveCharacterTextSplitter was removed as it was not being used in the code. The instantiation of TextSplitter was fixed by removing the unnecessary check for RecursiveCharacterTextSplitter and simplifying the code.
🔥 refactor(loading.py): remove unused import of RecursiveCharacterTextSplitter
The commit changes the comparison operator from '==' to 'is' to compare object types. This is because 'is' compares the object identity while '==' compares the object value. In this case, we want to compare the object identity, so 'is' is the correct operator to use.
🐛 fix(loading.py): fix type hinting in instantiate_embedding function
🔨 refactor(loading.py): add type hinting to instantiate_textsplitter function
The changes in this commit add type hinting to the `instantiate_agent`, `instantiate_embedding`, and `instantiate_textsplitter` functions to improve code readability and maintainability. The `instantiate_embedding` function had a bug in its type hinting which has been fixed.
Added documentation links to the vectorstores integrations in the config.yaml file. This will make it easier for developers to access the documentation for each integration.
The RecursiveCharacterTextSplitter class in textsplitters.py now has a new field called separator_type. This field is used to specify the type of separator to be used in the splitter. The separator_type field is a string and can take any value from the Language enum or "Text". This change was made to improve the flexibility of the RecursiveCharacterTextSplitter class.
This commit adds type hints to the function parameters and return types in the loading.py file. This improves the readability and maintainability of the codebase by making it easier to understand the expected types of the parameters and return values of the functions.
Added documentation links for new integrations and memories to improve the documentation of the project. The new integrations are Cohere and HuggingFaceHub, and the new memories are ConversationBufferWindowMemory and VectorStoreRetrieverMemory.
The VectorStoreFrontendNode class now has VectorStoreRetriever as an extra base class in addition to BaseRetriever. This change was made to improve the functionality of the class by allowing it to inherit from VectorStoreRetriever.
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.
This commit adds documentation links for the LlamaCpp and CTransformers integrations in the config.yaml file. The links point to the relevant documentation pages on the LangChain website. This improves the accessibility of the documentation for these integrations.
✨ 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 default values of the settings attributes were changed from an empty list to an empty dictionary. This change was made to avoid errors that could occur when trying to access a non-existent key in the dictionary.
✨ feat(frontend_node): add documentation field to the frontend node dict representation
The `set_documentation` method is added to the `FrontendNode` class to allow setting the documentation of the frontend node. The `to_dict` method is updated to include the `documentation` field in the dict representation of the frontend node. This improves the readability and usability of the frontend node by providing documentation for the node.
This commit adds a new property to the LangChainTypeCreator class called docs_map, which is a dictionary that maps the name of the component to its documentation link. The docs_map property is used to set the documentation of the component in the signature of the component. This change improves the readability and maintainability of the code by making it easier to add and update documentation for components.
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.
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.
The fields in the Template class were previously sorted by DIRECT_TYPES, which caused issues when fields had the same field_type. Sorting alphabetically first ensures that fields are sorted in a consistent manner before sorting by DIRECT_TYPES.
The `instantiate_vectorstore` function now uses a dictionary to initialize vector stores instead of a series of if-else statements. This improves the readability and maintainability of the code. A new dictionary `vecstore_initializer` is added to `vector_store.py` to map the class names of vector stores to their respective initialization functions.
The `instantiate_vectorstore` function now supports the `MongoDBAtlasVectorSearch` vector store. This allows for the use of MongoDB Atlas as a vector store for Langflow. The `search_kwargs` parameter is now supported for all vector stores that have a `as_retriever` method. This allows for the configuration of the vector store's search parameters.
The hardcoded values for db_name, collection_name, and index_name have been removed from the initialize_mongodb function and are now required parameters. This makes the function more flexible and allows it to be used with different databases and collections. The support for the index_name parameter has been added to the MongoDBAtlasVectorSearch template in vectorstores.py, which allows the user to specify the name of the index to be used in the search.
🐛 fix(vector_store.py): remove hardcoded values for db_name, collection_name, and index_name and make them required parameters
