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 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 SlackSVG component was renamed to MongoDBSVG to better reflect the actual icon being used. This improves the naming consistency and makes the code more readable.
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 certifi package is added to the dev dependencies to ensure that the package is available during development. This package provides Mozilla's carefully curated collection of Root Certificates for validating the trustworthiness of SSL certificates while making HTTPS requests.
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
The MongoDBIcon component was added to the frontend app to be used as an icon for MongoDB Atlas Vector Search. The icon was added as an SVG file and imported as a React component. The component was then added to the nodeIcons object in the utils.ts file.
✨ feat(langflow): add support for search_kwargs field in VectorStoreFrontendNode
The changes add support for MongoDB Atlas Vector Search in the vectorstores. The `MongoDBAtlasVectorSearch` class is now imported and initialized in `vector_store.py`. The `initialize_mongodb` function is added to initialize the MongoDB Atlas Vector Search class. The `VectorStoreFrontendNode` class is updated to add the `mongodb_atlas_cluster_uri`, `collection_name`, and `db_name` fields. The `search_kwargs` field is also added to the `VectorStoreFrontendNode` class to allow users to pass additional search parameters to the vector store.
The type hinting for allowed_tools variable is unnecessary as it is already defined in the previous line. Removing the type hinting improves the readability of the code.
The ternary operator in the validateNode function was simplified by removing the unnecessary if statement. The code is now more concise and easier to read.
The test now includes an assertion to check if the result of the function call is not None. This ensures that the function is returning a value and that the test is checking the correct output.
Added assertions to test_build_template_from_function to ensure that the returned result is not None and that the expected keys are present in the result. This improves the reliability of the test and ensures that the function is working as expected.
🔨 refactor(utils.ts): simplify getConnectedNodes function
🔨 refactor(utils.ts): remove unused variable in groupByFamily function
The snakeToSpaces function has been simplified by removing the unnecessary variable declaration. The getConnectedNodes function has been simplified by removing the unnecessary variable declaration and returning the result directly. The groupedObj variable in the groupByFamily function is no longer used, so it has been removed.
The display name for the SupabaseVectorStore is now set to "Supabase". This improves the user experience by providing a more descriptive name for the vector store.
The test_build_params function was failing when the root node was None. This commit adds an assertion to check if the root node is not None before proceeding with the other assertions.
The default value for the OpenAI model in the chat field has been updated to "gpt-3.5-turbo-0613" to reflect the latest version of the model. The default value for the OpenAI model in the text field has been updated to "text-davinci-003" to reflect the latest version of the model. This ensures that the tests are using the latest and most accurate models for OpenAI.
The `sort_fields` method has been added to the `Template` class to sort fields based on the `DIRECT_TYPES` constant. Fields that have a `field_type` in `DIRECT_TYPES` are sorted first, followed by the remaining fields. This ensures that fields that have a direct type are processed first, which is important for the correct functioning of the template.
The DIRECT_TYPES constant was removed from the vertex and graph modules as it is now defined in the utils module. This change improves code organization and reduces duplication.
The format_dict function was updated to set a default value for the model_name key in the value dictionary for the OpenAI, ChatOpenAI, and Anthropic models. This ensures that the model_name key always has a value, even if the options list is empty.
✨ feat(chains.py): add TemplateField 'chain_type' to support different types of QA chains
The 'memory' field was previously set to required=False, but it is actually required for the chain to function properly. This fix sets required=True for the 'memory' field.
A new TemplateField 'chain_type' has been added to support different types of QA chains. This field is of type 'str', is required, and is a list of options. It allows the user to select the type of QA chain they want to use.
The advanced field was set to True for input_key and output_key fields, which made them appear in the advanced section of the UI. This was not intended, so the advanced field is now set to False for these fields.
🐛 fix(process.py): make inputs optional in process_graph_cached function
The inputs and tweaks parameters in the process_flow endpoint are now optional, which allows for more flexibility in the API. The inputs parameter in the process_graph_cached function is now optional, which prevents a ValueError from being raised when a Chain object is processed without inputs.
The memory_key field is now set to "chat_history" by default. This change ensures that the memory_key field is always initialized with a default value, which is useful for the application's functionality.
🔨 refactor(frontend): simplify conditional rendering in InputFileComponent component
🔨 refactor(frontend): simplify arrow function in SupabaseIcon component
The empty object destructuring in the LoadingSpinner component is unnecessary and can be removed. The conditional rendering in the InputFileComponent component can be simplified by removing unnecessary parentheses. The arrow function in the SupabaseIcon component can be simplified by removing unnecessary parentheses.
The types-appdirs package was added to the poetry dependencies to provide type hints for the appdirs package. This improves the codebase's maintainability and readability by providing better type checking and documentation.
The import statements for the weaviate and pinecone libraries were causing import errors. Adding the `# type: ignore` comment suppresses these errors and allows the code to run without issues.
This commit adds type hinting to the function arguments of `get_result_and_thought` and `process_graph_cached` functions in `process.py` file. This improves code readability and maintainability.
This commit updates the langchain dependency from version 0.0.208 to version 0.0.209. This is a minor version update and is done to keep the dependency up-to-date with the latest features and bug fixes.
🐛 fix(graph.py): change message variable to a dictionary to match the expected input of get_result_and_thought function and update the assertion to check if the result is a dictionary instead of a string
The test for agents_template.py was updated to include the openai-multi-functions agent in the list of agents. This was done to ensure that the test coverage for the agent is complete.
The test for graph.py was updated to change the message variable to a dictionary to match the expected input of the get_result_and_thought function. The assertion was also updated to check if the result is a dictionary instead of a string. This was done to ensure that the test coverage for the function is complete.
The `initialize_chroma` function had redundant code that was removed. The `embedding_function` parameter was renamed to `embedding` to match the parameter name used in the `class_object` constructor. The `documents` and `texts` parameters were being used interchangeably, so the code was updated to use only `documents`.
The `name` parameter in the `format_field` method of the `DocumentLoaderFrontNode` class now uses the `Optional` type hint to indicate that it can be None. This improves the code's readability and makes it easier to understand the expected behavior of the method.
The function now checks if "texts" is in the params dictionary and renames it to "documents" for consistency. The "supabase_url" and "supabase_service_key" are now removed from the params dictionary and passed directly to the create_client function. The function also removes the "documents" and "texts" keys from the params dictionary if there are no documents in the params. This improves the readability of the code and removes redundant code.
The log level of the sorted vertices in the generator_build method of the Graph class has been changed from info to debug. This is because the sorted vertices are not critical information and are only useful for debugging purposes.
✨ feat(vector_store.py): add support for Supabase client object to be passed in as a parameter
The 'texts' parameter has been renamed to 'documents' to improve semantics. This change makes it clearer that the parameter is a list of documents. Additionally, support for a Supabase client object has been added as a parameter. This allows for more flexibility in the initialization of the SupabaseVectorStore class.
