You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Version 2 Langflow repo to DragDropAIAgentBuilder repo and fixed the merge conflict (#228)
* fixed the merge conflict
* fix the main ruff check style
* fix the flows issue
* added new modifed file in main
* fix the docker issue
* fix the ruff check issue
* part 3 ruff checks files like in test
* debug the issues
* working all the dir
Copy file name to clipboardExpand all lines: .devcontainer/README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
These instructions will walk you through the process of running a Langflow demo via GitHub Codespaces.
4
4
5
-
If you want a faster and easier demo experience with Langflow, DataStax Langflow is a hosted environment with zero setup: [Sign up for a free account.](https://astra.datastax.com/signup?type=langflow)
5
+
If you want a faster and easier demo experience with Langflow, download and install [Langflow Desktop](https://docs.langflow.org/get-started-installation#install-and-run-langflow-desktop) for the least complicated setup experience.
There are two options available to you: the 'easy' and recommended option is to use a Development Container ("[Dev Container](https://containers.dev/)"), or you can choose to use your own OS / environment.
34
+
There are two options available to you: use your local environment with `make` commands (recommended for macOS and Linux), or use a Development Container ("[Dev Container](https://containers.dev/)") which is recommended for Windows users.
35
35
36
-
### Option 1 (Preferred): Use a Dev Container
37
-
38
-
Open this repository as a Dev Container per your IDEs instructions.
39
-
40
-
#### Microsoft VS Code
41
-
42
-
- See [Developing inside a Container](https://code.visualstudio.com/docs/devcontainers/containers)
43
-
- You may also find it helpful to [share `git` credentials](https://code.visualstudio.com/remote/advancedcontainers/sharing-git-credentials) with the container
44
-
45
-
### Option 2: Use Your Own Environment
36
+
### Option 1 (Recommended): Use Your Local Environment
46
37
47
38
Install Pre-Requisites:
48
39
49
-
-**Operating System**: macOS or Linux; Windows users **_MUST_** develop under WSL.
40
+
-**Operating System**: macOS or Linux; Windows users should use WSL or consider Option 2 (Dev Container).
50
41
-**`git`**: The project uses the ubiquitous `git` tool for change control.
51
-
-**`make`**: The project uses `make` to coordidinate packaging.
42
+
-**`make`**: The project uses `make` to coordinate packaging.
52
43
-**`uv`**: This project uses `uv` (`>=0.4`), a Python package and project manager from Astral. Install instructions at https://docs.astral.sh/uv/getting-started/installation/.
53
44
-**`npm`**: The frontend files are built with Node.js (`v22.12 LTS`) and `npm` (`v10.9`). Install instructions at https://nodejs.org/en/download/package-manager.
54
45
- Windows (WSL) users: ensure `npm` is installed within WSL environment; `which npm` should resolve to a Linux location, not a Windows location.
55
46
47
+
### Option 2: Use a Dev Container (Recommended for Windows)
48
+
49
+
Open this repository as a Dev Container per your IDEs instructions.
50
+
51
+
A preconfigured `.devcontainer` is included in this repository and is auto-detected by supported IDEs.
52
+
53
+
#### Microsoft VS Code
54
+
55
+
To start the preconfigured `.devcontainer` with the VS Code Dev Containers extension, from the Command Palette, run the Dev Containers: Reopen in Container command.
56
+
57
+
- See [Developing inside a Container](https://code.visualstudio.com/docs/devcontainers/containers)
58
+
- You may also find it helpful to [share `git` credentials](https://code.visualstudio.com/remote/advancedcontainers/sharing-git-credentials) with the container
59
+
56
60
### Initial Environment Validation
57
61
58
62
To setup and validate the initial environment, run:
@@ -118,6 +122,25 @@ The backend service runs as a FastAPI service on Python, and is responsible for
118
122
make backend
119
123
```
120
124
125
+
> [!TIP]
126
+
> **Component Development Mode**: By default, Langflow uses a prebuilt component index for fast startup (~10ms). If you're actively developing or modifying components, enable dynamic component loading with `LFX_DEV`:
127
+
>
128
+
> ```bash
129
+
># Load all components dynamically
130
+
> LFX_DEV=1 make backend
131
+
>
132
+
># Load only specific component modules (faster dev workflow)
133
+
> LFX_DEV=mistral,openai,anthropic make backend
134
+
>```
135
+
>
136
+
> The list mode is particularly useful when working on specific integrations, as it significantly speeds up startup time by only loading the components you need.
137
+
>
138
+
> Without `LFX_DEV`, component changes require rebuilding the index:
139
+
>
140
+
>```bash
141
+
> uv run python scripts/build_component_index.py
142
+
>```
143
+
121
144
You will get output similar to:
122
145
123
146
```
@@ -181,9 +204,18 @@ Navigate to http://localhost:3001/ in a browser and view the documentation. Docu
181
204
182
205
Components reside in folders under `src/backend/base/langflow`, and their unit tests under `src/backend/base/tests/unit/components`.
183
206
207
+
> [!IMPORTANT]
208
+
> **Component Development Mode**: When actively developing components, make sure to run the backend with `LFX_DEV=1` to enable live reloading:
209
+
>
210
+
> ```bash
211
+
> LFX_DEV=1 make backend
212
+
> ```
213
+
>
214
+
> This ensures your component changes are immediately reflected without needing to rebuild the component index.
215
+
184
216
### Adding a Component
185
217
186
-
Add the component to the appropriate subdirectory, and add the component to the `__init__.py` file (alphabetical ordering on the `import` and the `__all__` list). Assuming the backend and frontend services are running, the backend service will restart as these files are changed. The new component will be visible after the backend is restarted, _*and*_ after you hit "refresh" in the browser.
218
+
Add the component to the appropriate subdirectory, and add the component to the `__init__.py` file (alphabetical ordering on the `import` and the `__all__` list). Assuming the backend and frontend services are running **with `LFX_DEV=1`**, the backend service will restart as these files are changed. The new component will be visible after the backend is restarted, _*and*_ after you hit "refresh" in the browser.
187
219
188
220
> [!TIP]
189
221
> It is faster to copy-paste the component code from your editor into the UI _without_ saving in the source code in the editor, and once you are satisfied it is working you can save (restarting the backend) and refresh the browser to confirm it is present.
@@ -197,6 +229,16 @@ Modifying a component is much the same as adding a component: it is generally ea
197
229
> [!NOTE]
198
230
> If you have an old version of the component on the canvas when changes are saved and the backend service restarts, that component should show "Updates Available" when the canvas is reloaded (i.e. a browser refresh). [Issue 5179](https://github.com/langflow-ai/langflow/issues/5179) indicates this behavior is not consistent, at least in a development setting.
199
231
232
+
### Component Index
233
+
234
+
When you're done modifying components and ready to commit, the component index will be automatically updated by CI when you create a pull request. The GitHub Actions workflow will detect changes to components and rebuild the index, committing it to your PR branch if needed.
235
+
236
+
If you want to manually rebuild the index locally for testing:
237
+
238
+
```bash
239
+
uv run python scripts/build_component_index.py
240
+
```
241
+
200
242
## Building and Testing Changes
201
243
202
244
When you are ready to commit, and before you commit, you should consider the following:
Copy file name to clipboardExpand all lines: README.md
+52-23Lines changed: 52 additions & 23 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,32 +1,23 @@
1
1
<!-- markdownlint-disable MD030 -->
2
2
3
-
[Drag and Drop AI Agent Builder](https://visualaiagentsbuilder.org) is a powerful tool for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and a built-in API server that turns every agent into an API endpoint that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
> - Langflow versions 1.6.0 through 1.6.3 have a critical bug where `.env` files are not read, potentially causing security vulnerabilities. **DO NOT** upgrade to these versions if you use `.env` files for configuration. Instead, upgrade to 1.6.4, which includes a fix for this bug.
19
-
> - Windows users of Langflow Desktop should **not** use the in-app update feature to upgrade to Langflow version 1.6.0. For upgrade instructions, see [Windows Desktop update issue](https://docs.langflow.org/release-notes#windows-desktop-update-issue).
20
-
> - Users must update to Langflow >= 1.3 to protect against [CVE-2025-3248](https://nvd.nist.gov/vuln/detail/CVE-2025-3248)
21
-
> - Users must update to Langflow >= 1.5.1 to protect against [CVE-2025-57760](https://github.com/langflow-ai/langflow/security/advisories/GHSA-4gv9-mp8m-592r)
22
-
>
23
-
> For security information, see our [Security Policy](./SECURITY.md) and [Security Advisories](https://github.com/langflow-ai/langflow/security/advisories).
24
-
25
-
[Langflow](https://langflow.org) is a powerful tool for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
16
+
[Langflow](https://langflow.org) is a powerful platform for building and deploying AI-powered agents and workflows. It provides developers with both a visual authoring experience and built-in API and MCP servers that turn every workflow into a tool that can be integrated into applications built on any framework or stack. Langflow comes with batteries included and supports all major LLMs, vector databases and a growing library of AI tools.
26
17
27
18
## ✨ Highlight features
28
19
29
-
-**Visual builder interface** to quickly get started and iterate.
20
+
-**Visual builder interface** to quickly get started and iterate.
30
21
-**Source code access** lets you customize any component using Python.
31
22
-**Interactive playground** to immediately test and refine your flows with step-by-step control.
32
23
-**Multi-agent orchestration** with conversation management and retrieval.
@@ -35,29 +26,68 @@
35
26
-**Observability** with LangSmith, LangFuse and other integrations.
36
27
-**Enterprise-ready** security and scalability.
37
28
29
+
## 🖥️ Langflow Desktop
30
+
31
+
Langflow Desktop is the easiest way to get started. It includes dependency management and automatic updates.
Langflow requires [Python 3.10 to 3.13](https://www.python.org/downloads/release/python-3100/) and [uv](https://docs.astral.sh/uv/getting-started/installation/).
38
+
### Install locally (recommended)
41
39
42
-
1. To install Langflow, run:
40
+
Requires Python 3.10–3.13 and [uv](https://docs.astral.sh/uv/getting-started/installation/) (recommended package manager).
43
41
42
+
#### Install
43
+
44
+
From a fresh directory, run:
44
45
```shell
45
46
uv pip install langflow -U
46
47
```
47
48
48
-
2. To run Langflow, run:
49
+
The latest Langflow package is installed.
50
+
For more information, see [Install and run the Langflow OSS Python package](https://docs.langflow.org/get-started-installation#install-and-run-the-langflow-oss-python-package).
51
+
52
+
#### Run
49
53
54
+
To start Langflow, run:
50
55
```shell
51
56
uv run langflow run
52
57
```
53
58
54
-
3. Go to the default Langflow URL at `http://127.0.0.1:7860`.
59
+
Langflow starts at http://127.0.0.1:7860.
60
+
61
+
That's it! You're ready to build with Langflow! 🎉
62
+
63
+
## 📦 Other install options
64
+
65
+
### Run from source
66
+
If you've cloned this repository and want to contribute, run this command from the repository root:
67
+
```shell
68
+
make run_cli
69
+
```
70
+
For more information, see [DEVELOPMENT.md](./DEVELOPMENT.md).
71
+
72
+
### Docker
73
+
Start a Langflow container with default settings:
74
+
```shell
75
+
docker run -p 7860:7860 langflowai/langflow:latest
76
+
```
77
+
Langflow is available at http://localhost:7860/.
78
+
For configuration options, see the [Docker deployment guide](https://docs.langflow.org/deployment-docker).
55
79
56
-
For more information about installing Langflow, including Docker and Desktop options, see [Install Langflow](https://docs.langflow.org/get-started-installation).
80
+
> [!CAUTION]
81
+
> - Langflow versions 1.6.0 through 1.6.3 have a critical bug where `.env` files are not read, potentially causing security vulnerabilities. **DO NOT** upgrade to these versions if you use `.env` files for configuration. Instead, upgrade to 1.6.4, which includes a fix for this bug.
82
+
> - Windows users of Langflow Desktop should **not** use the in-app update feature to upgrade to Langflow version 1.6.0. For upgrade instructions, see [Windows Desktop update issue](https://docs.langflow.org/release-notes#windows-desktop-update-issue).
83
+
> - Users must update to Langflow >= 1.3 to protect against [CVE-2025-3248](https://nvd.nist.gov/vuln/detail/CVE-2025-3248)
84
+
> - Users must update to Langflow >= 1.5.1 to protect against [CVE-2025-57760](https://github.com/langflow-ai/langflow/security/advisories/GHSA-4gv9-mp8m-592r)
85
+
>
86
+
> For security information, see our [Security Policy](./SECURITY.md) and [Security Advisories](https://github.com/langflow-ai/langflow/security/advisories).
57
87
58
-
## 📦 Deployment
88
+
## 🚀 Deployment
59
89
60
-
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to use Docker to deploy Langflow, see the [Docker deployment guide](https://docs.langflow.org/deployment-docker).
90
+
Langflow is completely open source and you can deploy it to all major deployment clouds. To learn how to deploy Langflow, see our [Langflow deployment guides](https://docs.langflow.org/deployment-overview).
61
91
62
92
## ⭐ Stay up-to-date
63
93
@@ -76,4 +106,3 @@ We welcome contributions from developers of all levels. If you'd like to contrib
0 commit comments