Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
http://www.langflow.org
d676aef9b4* feat: Implement serialization functions for various data types and add a unified serialize method * feat: Enhance serialization by adding support for primitive types, enums, and generic types * fix: Update Pinecone integration to use VectorStore and handle import errors gracefully * test: Add hypothesis-based tests for serialization functions across various data types * refactor: Replace custom serialization logic with unified serialize function for consistency and maintainability * refactor: Replace recursive serialization function with unified serialize method for improved clarity and maintainability * refactor: Replace custom serialization logic with unified serialize function for improved consistency and clarity * refactor: Enhance serialization logic by adding instance handling and streamlining type checks * refactor: Remove custom dictionary serialization from ResultDataResponse for streamlined handling * refactor: Enhance serialization in ResultDataResponse by adding max_items_length for improved handling of outputs, logs, messages, and artifacts * refactor: Move MAX_ITEMS_LENGTH and MAX_TEXT_LENGTH constants to serialization module for better organization * refactor: Simplify message serialization in Log model by utilizing unified serialize function * refactor: Remove unnecessary pytest marker from TestSerializationHypothesis class * optimize _serialize_bytes Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com> * feat: Add support for numpy integer type serialization * feat: Enhance serialization with support for pandas and numpy types * test: Add comprehensive serialization tests for numpy and pandas types * fix: Update _serialize_dispatcher to return string representation for unsupported types * fix: Update _serialize_dispatcher to return the object directly instead of its string representation * optmize conditional Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com> * optimize length check Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com> * fix: Update string and list truncation to include ellipsis for clarity * ⚡️ Speed up function `_serialize_dataframe` by 123% in PR #6044 (`refactor-serialization`) Certainly! Here's a more efficient version of the given program. The primary optimization performed here is removing the redundant `.apply()` call and directly truncating values in a more performant way. ### Changes Made. 1. **Removed redundant `apply` calls**: In the original code, there were nested `apply` calls which can be very slow on larger DataFrames. The new implementation converts the DataFrame to a list of dictionaries first and then truncates the values if needed. 2. **Optimized truncation logic**: Applied truncation directly while iterating over the dictionary after conversion from a DataFrame. This reduces overhead and improves readability. These changes should enhance the runtime performance of the serialization process, especially for larger DataFrames. --------- Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org> Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com> |
||
|---|---|---|
| .devcontainer | ||
| .github | ||
| .vscode | ||
| deploy | ||
| docker | ||
| docker_example | ||
| docs | ||
| scripts | ||
| src | ||
| test-results | ||
| .env.example | ||
| .eslintrc.json | ||
| .gitattributes | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| DEVELOPMENT.md | ||
| eslint.config.js | ||
| LICENSE | ||
| Makefile | ||
| pyproject.toml | ||
| README.ES.md | ||
| README.FR.md | ||
| README.ja.md | ||
| README.KR.md | ||
| README.md | ||
| README.PT.md | ||
| README.zh_CN.md | ||
| render.yaml | ||
| uv.lock | ||
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Docs - Free Cloud Service - Self Managed
✨ Core features
- Python-based and agnostic to models, APIs, data sources, or databases.
- Visual IDE for drag-and-drop building and testing of workflows.
- Playground to immediately test and iterate workflows with step-by-step control.
- Multi-agent orchestration and conversation management and retrieval.
- Free cloud service to get started in minutes with no setup.
- Publish as an API or export as a Python application.
- Observability with LangSmith, LangFuse, or LangWatch integration.
- Enterprise-grade security and scalability with free DataStax Langflow cloud service.
- Customize workflows or create flows entirely just using Python.
- Ecosystem integrations as reusable components for any model, API or database.
📦 Quickstart
- Install with uv (recommended) (Python 3.10 to 3.12):
uv pip install langflow
- Install with pip (Python 3.10 to 3.12):
pip install langflow
- Cloud: DataStax Langflow is a hosted environment with zero setup. Sign up for a free account.
- Self-managed: Run Langflow in your environment. Install Langflow to run a local Langflow server, and then use the Quickstart guide to create and execute a flow.
- Hugging Face: Clone the space using this link to create a Langflow workspace.
⭐ Stay up-to-date
Star Langflow on GitHub to be instantly notified of new releases.
👋 Contribute
We welcome contributions from developers of all levels. If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.