jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions
Langflow is a powerful tool for building and deploying AI-powered agents and workflows. http://www.langflow.org
13,266 commits 2 branches 1 tag 544 MiB
Find a file
Gabriel Luiz Freitas Almeida 5ef84f7911
 feat: add CrewAI components and refactor codebase (#2647) 
* feat: Add CrewAI icon component

This commit adds the CrewAI icon component to the project. The component is imported and used in the styleUtils file, allowing it to be used throughout the application. This addition enhances the visual representation of the CrewAI feature in the user interface.

* feat: Add CrewAI[tools] dependency to project

This commit adds the CrewAI dependency to the project by including it in the pyproject.toml file. The version specified is "^0.36.0" and the "tools" extras are included. This addition allows the project to utilize the features provided by CrewAI.

* fix: update crewai icon size

* feat: Add CrewAIAgent component

This commit adds the CrewAIAgent component to the project. The component represents an agent of CrewAI and includes various inputs and outputs for role, goal, backstory, tools, language model, memory, verbosity, and delegation. This addition enhances the functionality of the project by integrating with CrewAI and allows for more advanced agent-based interactions.

* feat: Add CrewAICrew component

This commit adds the CrewAICrew component to the project. The component represents a group of agents and defines how they should collaborate and the tasks they should perform. It includes various inputs and outputs for tasks, agents, topic, verbosity, memory, cache, max RPM, process, and more. This addition enhances the functionality of the project by integrating with CrewAI and allows for more advanced agent-based interactions.

* feat: Add CrewAITask component

This commit adds the CrewAITask component to the project. The component represents a task in CrewAI and includes inputs for description, expected output, tools, agent, and async execution. It also provides an output for the task itself. This addition enhances the functionality of the project by integrating with CrewAI and allows for the creation and execution of tasks within the system.

* refactor: Update build configuration in custom_component_update endpoint

This commit updates the build configuration in the custom_component_update endpoint of the endpoints.py file. The previous implementation was assigning the result of code_request.get_template() directly to the build_config parameter, which caused an issue. The updated code now assigns the result to the updated_build_config variable before passing it to the cc_instance.update_build_config() method. This change ensures that the correct build configuration is used and improves the functionality of the custom_component_update endpoint.

* feat: Add SequentialTask and HierarchicalTask classes

This commit adds the SequentialTask and HierarchicalTask classes to the tasks.py file in the base/agents/crewai directory. These classes represent different types of tasks in the CrewAI system. The SequentialTask class is used for sequential tasks, while the HierarchicalTask class is used for hierarchical tasks. This addition enhances the functionality of the project by providing the necessary classes for implementing different types of tasks in CrewAI.

* refactor: Update CrewAIAgentComponent class name

This commit updates the class name from "CrewAIAgent" to "CrewAIAgentComponent" in the CrewAIAgent.py file. The new name better reflects the nature of the class as a component and improves the clarity of the codebase.

* refactor: Update CrewAICrewSequential component

This commit adds the CrewAICrewSequential component to the project. The component represents a group of agents and defines how they should collaborate and the tasks they should perform in a sequential manner. It includes various inputs and outputs for tasks, verbosity, memory, cache, max RPM, and more. This addition enhances the functionality of the project by providing a specific component for sequential tasks in the CrewAI system.

* feat: Add CrewAICrewHierarchical component

This commit adds the CrewAICrewHierarchical component to the project. The component represents a group of agents and defines how they should collaborate and the tasks they should perform in a hierarchical manner. It includes various inputs and outputs for tasks, verbosity, memory, cache, max RPM, and more. This addition enhances the functionality of the project by providing a specific component for hierarchical tasks in the CrewAI system.

* refactor: Rename CrewAITask.py to CrewAITaskHierarchical.py

This commit renames the file "CrewAITask.py" to "CrewAITaskHierarchical.py" in the "helpers" directory of the "langflow/components/helpers" package. The new name better reflects the purpose of the file, which is to define the "CrewAITaskHierarchical" component. This change improves the clarity and organization of the codebase.

* feat: Add CrewAITaskSequential component

This commit adds the CrewAITaskSequential component to the project. The component represents a sequential task in CrewAI and includes inputs for task description, expected output, tools, agent, and async execution. It also provides an output for the task itself. This addition enhances the functionality of the project by integrating with CrewAI and allows for the creation and execution of sequential tasks within the system.

* feat: Add BaseCrewComponent class

This commit adds the BaseCrewComponent class to the project. The class represents a group of agents, defining how they should collaborate and the tasks they should perform. It includes various inputs and outputs for tasks, verbosity, memory, cache, max RPM, and more. This addition enhances the functionality of the project by providing a base component for creating and managing crews in the CrewAI system.

* refactor: Update display name of CrewAIAgentComponent to "CrewAI Agent"

* refactor: Remove CrewAICrewHierarchical component

This commit removes the CrewAICrewHierarchical component from the project. The component represented a group of agents and defined how they should collaborate and the tasks they should perform in a hierarchical manner. However, it is no longer needed and has been deemed unnecessary for the current project requirements. This removal streamlines the codebase and improves the clarity of the project.

* refactor: make Crew use BaseCrew class

* refactor: Replace CrewAICrewSequential with SequentialCrew

This commit replaces the deprecated CrewAICrewSequential component with the new SequentialCrew component. The SequentialCrew component represents a group of agents and defines how they should collaborate and the tasks they should perform in a sequential manner. This change improves the clarity and organization of the codebase by using a more descriptive and consistent naming convention for the component. It also aligns with the recent refactorings in the project, such as the removal of the CrewAICrewHierarchical component and the addition of the BaseCrewComponent class. Overall, this update enhances the functionality and maintainability of the project.

* refactor: Rename CrewAITaskHierarchical.py to HierarchicalTask.py

This commit renames the file "CrewAITaskHierarchical.py" to "HierarchicalTask.py" in the "helpers" directory of the "langflow/components/helpers" package. The new name better reflects the purpose of the file, which is to define the "HierarchicalTask" component. This change improves the clarity and organization of the codebase.

* refactor: Rename CrewAITaskSequential.py to SequentialTask.py

This commit renames the file "CrewAITaskSequential.py" to "SequentialTask.py" in the "helpers" directory of the "langflow/components/helpers" package. The new name better reflects the purpose of the file, which is to define the "SequentialTaskComponent" component. This change improves the clarity and organization of the codebase.

* style: reorder imports

* chore: update lock

* refactor: Refactor build_crew method in BaseCrewComponent

This commit refactors the build_crew method in the BaseCrewComponent class. The method was previously taking tasks and agents as arguments, but it was not using them correctly. This update removes the unnecessary arguments and fixes the method to correctly build a Crew object. This refactor improves the clarity and functionality of the codebase.

* refactor: Update status assignment in CrewAIAgentComponent

This commit updates the status assignment in the CrewAIAgentComponent class. Previously, the status was set using the `model_dump()` method of the agent, but it has been changed to use the `repr()` method instead. This change improves the clarity and consistency of the codebase.

* refactor: Add agents input to HierarchicalCrewComponent

This commit adds the "agents" input to the HierarchicalCrewComponent class in the "HierarchicalCrew.py" file. The "agents" input is a list of "Agent" objects and allows for better management and collaboration between agents within the crew. This addition enhances the functionality and flexibility of the HierarchicalCrewComponent, improving the overall codebase.

* refactor: Fix post_process_raw function in artifact.py

This commit fixes the post_process_raw function in the artifact.py file. Previously, the function was not correctly handling the case when the raw data was a BaseModel or a dictionary. This update ensures that the raw data is properly encoded using jsonable_encoder and updates the artifact_type accordingly. This fix improves the functionality and reliability of the codebase.

* refactor: Update CustomComponent's repr_value handling

This commit updates the repr_value handling in the CustomComponent class. Previously, the repr_value was being modified directly within the class, which could lead to unexpected behavior. This update ensures that the repr_value is returned instead of modifying it directly. Additionally, it adds proper handling for different types of repr_value, such as dictionaries and BaseModel objects. This refactor improves the clarity and maintainability of the codebase.

* update lock

* refactor: Add task input to SequentialTaskComponent

This commit adds the "task" input to the SequentialTaskComponent class in the "SequentialTask.py" file. The "task" input is a SequentialTask object that will perform the task. This addition enhances the functionality and flexibility of the SequentialTaskComponent, improving the overall codebase.

* refactor: Change log level of file retrieval message in LocalStorageService

* refactor(crew.py): update import statement to include InputTypes from langflow.inputs.inputs module to enhance code readability and maintainability

* chore: Update cachetools dependency to version 5.4.0

* feat(crew.py): add new methods get_task_callback and get_step_callback to handle task and step callbacks respectively

* refactor: Add allow_code_execution input to CrewAIAgentComponent

This commit adds the "allow_code_execution" input to the CrewAIAgentComponent class in the "CrewAIAgent.py" file. The "allow_code_execution" input is a boolean value that determines whether the agent is allowed to execute code. This addition enhances the functionality and flexibility of the CrewAIAgentComponent, improving the overall codebase.

* Add step_callback and task_callback inputs to HierarchicalCrewComponent and SequentialCrewComponent

* style(SequentialTask.py): remove unnecessary 'required' attribute from input definition in SequentialTaskComponent class

* chore: fix lint issues
2024-07-15 16:56:47 -07:00
.devcontainer Update Python base image to version 3.10 in devcontainer.json 2024-04-17 11:21:05 -03:00
.github chore: move test-cli job to run separately from unit tests (#2712) 2024-07-15 13:33:30 -07:00
.vscode feat: add opentelemetry utility functions and unit tests (#2570) 2024-07-10 15:01:38 -04:00
deploy fix: fix docker compose and add instructions (#2654) 2024-07-12 09:27:13 -07:00
docker chore: simplify docker (#2526) 2024-07-04 11:14:52 -03:00
docker_example chore: simplify docker (#2526) 2024-07-04 11:14:52 -03:00
docs docs: add CNAME file for custom domain (#2685) 2024-07-13 01:21:22 -07:00
scripts Bump braces from 3.0.2 to 3.0.3 in /scripts/aws 2024-07-01 13:53:39 -03:00
src feat: add CrewAI components and refactor codebase (#2647) 2024-07-15 16:56:47 -07:00
tests refactor: runnable_vertices_manager.py (#2646) 2024-07-15 17:57:00 +00:00
.env.example fixing ThreadingInMemoryCache usage (#2604) 2024-07-10 04:52:37 -07:00
.eslintrc.json 🔧 (.pre-commit-config.yaml): Add eslint@9.1.1 as a dependency and enable autofix for pretty-format-json hook 2024-05-02 19:27:40 -03:00
.gitattributes refactor: Update .gitattributes to remove working-tree-encoding for .mdx and .json files 2024-06-10 14:30:27 -03:00
.gitignore fixing ThreadingInMemoryCache usage (#2604) 2024-07-10 04:52:37 -07:00
.pre-commit-config.yaml Update linting workflows for frontend and Python code (#2171) 2024-06-14 06:27:48 -07:00
CODE_OF_CONDUCT.md run codespell 2024-06-04 09:26:13 -03:00
CONTRIBUTING.md docs(contributing.md): update contribution guidelines 2024-06-22 19:13:33 -03:00
eslint.config.js 🔧 (.pre-commit-config.yaml): Add eslint@9.1.1 as a dependency and enable autofix for pretty-format-json hook 2024-05-02 19:27:40 -03:00
LICENSE Update organization name and URLs in configuration files 2024-04-18 11:58:19 -03:00
Makefile chore: simplify docker (#2526) 2024-07-04 11:14:52 -03:00
poetry.lock feat: add CrewAI components and refactor codebase (#2647) 2024-07-15 16:56:47 -07:00
pyproject.toml feat: add CrewAI components and refactor codebase (#2647) 2024-07-15 16:56:47 -07:00
README.md fixing ThreadingInMemoryCache usage (#2604) 2024-07-10 04:52:37 -07:00
README.PT.md feat: Update sidebar link to Langflow workspace 2024-06-24 04:37:06 -07:00
README.zh_CN.md Merge remote-tracking branch 'origin/dev' into two_edges 2024-06-07 10:42:22 -03:00
render.yaml update blueprint render 2024-07-01 13:53:55 -03:00

README.md

Langflow 1.0 is OUT! 🎉

Read all about it here!

Langflow

A visual framework for building multi-agent and RAG applications

Open-source, Python-powered, fully customizable, LLM and vector store agnostic

Docs - Join our Discord - Follow us on X - Live demo

README in English README in Portuguese README in Simplified Chinese

Your GIF

📝 Content

📦 Get Started

You can install Langflow with pip:

# Make sure you have >=Python 3.10 installed on your system.
python -m pip install langflow -U

Or

If you would like to install from your cloned repo, you can build and install Langflow's frontend and backend with:

make install_frontend && make build_frontend && make install_backend

Then, run Langflow with:

python -m langflow run

🎨 Create Flows

Creating flows with Langflow is easy. Simply drag components from the sidebar onto the workspace and connect them to start building your application.

Explore by editing prompt parameters, grouping components into a single high-level component, and building your own Custom Components.

Once you’re done, you can export your flow as a JSON file.

Load the flow with:

from langflow.load import run_flow_from_json

results = run_flow_from_json("path/to/flow.json", input_value="Hello, World!")

Deploy

DataStax Langflow

DataStax Langflow is a hosted version of Langflow integrated with AstraDB. Be up and running in minutes with no installation or setup required. Sign up for free.

Deploy Langflow on Hugging Face Spaces

You can also preview Langflow in HuggingFace Spaces. Clone the space using this link to create your own Langflow workspace in minutes.

Deploy Langflow on Google Cloud Platform

Follow our step-by-step guide to deploy Langflow on Google Cloud Platform (GCP) using Google Cloud Shell. The guide is available in the Langflow in Google Cloud Platform document.

Alternatively, click the "Open in Cloud Shell" button below to launch Google Cloud Shell, clone the Langflow repository, and start an interactive tutorial that will guide you through the process of setting up the necessary resources and deploying Langflow on your GCP project.

Open in Cloud Shell

Deploy on Railway

Use this template to deploy Langflow 1.0 on Railway:

Deploy on Railway

Deploy on Render

Deploy to Render

Deploy on Kubernetes

Follow our step-by-step guide to deploy Langflow on Kubernetes.

🖥️ Command Line Interface (CLI)

Langflow provides a command-line interface (CLI) for easy management and configuration.

Usage

You can run the Langflow using the following command:

langflow run [OPTIONS]

Each option is detailed below:

  • --help: Displays all available options.
  • --host: Defines the host to bind the server to. Can be set using the LANGFLOW_HOST environment variable. The default is 127.0.0.1.
  • --workers: Sets the number of worker processes. Can be set using the LANGFLOW_WORKERS environment variable. The default is 1.
  • --timeout: Sets the worker timeout in seconds. The default is 60.
  • --port: Sets the port to listen on. Can be set using the LANGFLOW_PORT environment variable. The default is 7860.
  • --env-file: Specifies the path to the .env file containing environment variables. The default is .env.
  • --log-level: Defines the logging level. Can be set using the LANGFLOW_LOG_LEVEL environment variable. The default is critical.
  • --components-path: Specifies the path to the directory containing custom components. Can be set using the LANGFLOW_COMPONENTS_PATH environment variable. The default is langflow/components.
  • --log-file: Specifies the path to the log file. Can be set using the LANGFLOW_LOG_FILE environment variable. The default is logs/langflow.log.
  • --cache: Selects the type of cache to use. Options are InMemoryCache and SQLiteCache. Can be set using the LANGFLOW_LANGCHAIN_CACHE environment variable. The default is SQLiteCache.
  • --dev/--no-dev: Toggles the development mode. The default is no-dev.
  • --path: Specifies the path to the frontend directory containing build files. This option is for development purposes only. Can be set using the LANGFLOW_FRONTEND_PATH environment variable.
  • --open-browser/--no-open-browser: Toggles the option to open the browser after starting the server. Can be set using the LANGFLOW_OPEN_BROWSER environment variable. The default is open-browser.
  • --remove-api-keys/--no-remove-api-keys: Toggles the option to remove API keys from the projects saved in the database. Can be set using the LANGFLOW_REMOVE_API_KEYS environment variable. The default is no-remove-api-keys.
  • --install-completion [bash|zsh|fish|powershell|pwsh]: Installs completion for the specified shell.
  • --show-completion [bash|zsh|fish|powershell|pwsh]: Shows completion for the specified shell, allowing you to copy it or customize the installation.
  • --backend-only: This parameter, with a default value of False, allows running only the backend server without the frontend. It can also be set using the LANGFLOW_BACKEND_ONLY environment variable.
  • --store: This parameter, with a default value of True, enables the store features, use --no-store to deactivate it. It can be configured using the LANGFLOW_STORE environment variable.

These parameters are important for users who need to customize the behavior of Langflow, especially in development or specialized deployment scenarios.

Environment Variables

You can configure many of the CLI options using environment variables. These can be exported in your operating system or added to a .env file and loaded using the --env-file option.

A sample .env file named .env.example is included with the project. Copy this file to a new file named .env and replace the example values with your actual settings. If you're setting values in both your OS and the .env file, the .env settings will take precedence.

👋 Contribute

We welcome contributions from developers of all levels to our open-source project on GitHub. If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.

Star History Chart

🌟 Contributors

langflow contributors

📄 License

Langflow is released under the MIT License. See the LICENSE file for details.