1.0 Alpha (#1599)
* Update model kwargs and temperature values
* Update keyboard shortcuts for advanced editing
* make Message field have no handles
* Update OpenAI API Key handling in OpenAIEmbeddingsComponent
* Remove unnecessary field_type key from CustomComponent class
* Update required field behavior in CustomComponent class
* Refactor AzureOpenAIModel.py: Removed unnecessary "required" attribute from input parameters
* Update BaiduQianfanChatModel and OpenAIModel configurations
* Fix range_spec step type validation
* Update RangeSpec step_type default value to "float"
* Fix Save debounce
* Update parameterUtils to use debounce instead of throttle
* Update input type options in schemas and graph base classes
* Refactor run_flow_with_caching endpoint to include simplified and experimental versions
* Add PythonFunctionComponent and test case for it
* Add nest_asyncio to fix event loop issue
* Refactor test_initial_setup.py to use RunOutputs instead of ResultData
* Remove unused code in test_endpoints.py
* Add asyncio loop to uvicorn command
* Refactor load_session method to handle coroutine result
* Fixed saving
* Fixed debouncing
* Add InputType and OutputType literals to schema.py
* Update input type in Graph class
* Add new schema for simplified API request
* Add delete_messages function and update test_successful_run assertions
* Add STREAM_INFO_TEXT constant to model components
* Add session_id to simplified_run_flow_with_caching endpoint
* Add field_typing import to OpenAIModel.py
* update starter projects
* Add constants for Langflow base module
* Update setup.py to include latest component versions
* Update Starter Examples
* sets starter_project fixture to Basic Prompting
* Refactor test_endpoints.py: Update test names and add new tests for different output types
* Update HuggingFace Spaces link and add image for dark mode
* Remove filepath reference
* Update Vertex params in base.py
* Add tests for different input types
* Add type annotations and improve test coverage
* Add duplicate space link to README
* Update HuggingFace Spaces badge in README
* Add Python 3.10 installation requirement to README
* Refactor flow running endpoints
* Refactor SimplifiedAPIRequest and add documentation for Tweaks
* Refactor input_request parameter in simplified_run_flow function
* Add support for retrieving specific component output
* Add custom Uvicorn worker for Langflow application
* Add asyncio loop to LangflowApplication initialization
* Update Makefile with new variables and start command
* Fix indentation in Makefile
* Refactor run_graph function to add support for running a JSON flow
* Refactor getChatInputField function and update API code
* Update HuggingFace Spaces documentation with duplication process
* Add asyncio event loop to uvicorn command
* Add installation of backend in start target
* udpate some starter projects
* Fix formatting in hugging-face-spaces.mdx
* Update installation instructions for Langflow
* set examples order
* Update start command in Makefile
* Add installation and usage instructions for Langflow
* Update Langflow installation and usage instructions
* Fix langflow command in README.md
* Fix broken link to HuggingFace Spaces guide
* Add new SVG assets for blog post, chat bot, and cloud docs
* Refactor example rendering in NewFlowModal
* Add new SVG file for short bio section
* Remove unused import and add new component
* Update title in usage.mdx
* Update HuggingFace Spaces heading in usage.mdx
* Update usage instructions in getting-started/usage.mdx
* Update cache option in usage documentation
* Remove 'advanced' flag from 'n_messages' parameter in MemoryComponent.py
* Refactor code to improve performance and readability
* Update project names and flow examples
* fix document qa example
* Remove commented out code in sidebars.js
* Delete unused documentation files
* Fix bug in login functionality
* Remove global variables from components
* Fix bug in login functionality
* fix modal returning to input
* Update max-width of chat message sender name
* Update styling for chat message component
* Refactor OpenAIEmbeddingsComponent signature
* Update usage.mdx file
* Update path in Makefile
* Add new migration and what's new documentation files
* Add new chapters and migration guides
* Update version to 0.0.13 in pyproject.toml
* new locks
* Update dependencies in pyproject.toml
* general fixes
* Update dependencies in pyproject.toml and poetry.lock files
* add padding to modal
* ✨ (undrawCards/index.tsx): update the SVG used for BasicPrompt component to undraw_short_bio_re_fmx0.svg to match the desired design
♻️ (undrawCards/index.tsx): adjust the width and height of the BasicPrompt SVG to 65% to improve the visual appearance
* Commented out components/data in sidebars.js
* Refactor component names in outputs.mdx
* Update embedded chat script URL
* Add data component and fix formatting in outputs component
* Update dependencies in poetry.lock and pyproject.toml
* Update dependencies in poetry.lock and pyproject.toml
* Refactor code to improve performance and readability
* Update dependencies in poetry.lock and pyproject.toml
* Fixed IO Modal updates
* Remove dead code at API Modal
* Fixed overflow at CodeTabsComponent tweaks page
* ✨ (NewFlowModal/index.tsx): update the name of the example from "Blog Writter" to "Blog Writer" for better consistency and clarity
* Update dependencies versions
* Update langflow-base to version 0.0.15 and fix setup_env script
* Update dependencies in pyproject.toml
* Lock dependencies in parallel
* Add logging statement to setup_app function
* Fix Ace not having type="module" and breaking build
* Update authentication settings for access token cookie
* Update package versions in package-lock.json
* Add scripts directory to Dockerfile
* Add setup_env command to build_and_run target
* Remove unnecessary make command in setup_env
* Remove unnecessary installation step in build_and_run
* Add debug configuration for CLI
* 🔧 chore(Makefile): refactor build_langflow target to use a separate script for updating dependencies and building
✨ feat(update_dependencies.py): add script to update pyproject.toml dependency version based on langflow-base version in src/backend/base/pyproject.toml
* Add number_of_results parameter to AstraDBSearchComponent
* Update HuggingFace Spaces links
* Remove duplicate imports in hugging-face-spaces.mdx
* Add number_of_results parameter to vector search components
* Fixed supabase not commited
* Revert "Fixed supabase not commited"
This reverts commit afb10a6262.
* Update duplicate-space.png image
* Delete unused files and components
* Add/update script to update dependencies
* Add .bak files to .gitignore
* Update version numbers and remove unnecessary dependencies
* Update langflow-base dependency path
* Add Text import to VertexAiModel.py
* Update langflow-base version to 0.0.16 and update dependencies
* Delete start projects and commit session in delete_start_projects function
* Refactor backend startup script to handle autologin option
* Update poetry installation script to include pipx update check
* Update pipx installation script for different operating systems
* Update Makefile to improve setup process
* Add error handling on streaming and fix streaming bug on error
* Added description to Blog Writer
* Sort base classes alphabetically
* Update duplicate-space.png image
* update position on langflow prompt chaining
* Add Langflow CLI and first steps documentation
* Add exception handling for missing 'content' field in search_with_vector_store method
* Remove unused import and update type hinting
* fix bug on egdes after creating group component
* Refactor APIRequest class and update model imports
* Remove unused imports and fix formatting issues
* Refactor reactflowUtils and styleUtils
* Add CLI documentation to getting-started/cli.mdx
* Add CLI usage instructions
* Add ZoomableImage component to first-steps.mdx
* Update CLI and first steps documentation
* Remove duplicate import and add new imports for ThemedImage and useBaseUrl
* Update Langflow CLI documentation link
* Remove first-steps.mdx and update index.mdx and sidebars.js
* Update Docusaurus dependencies
* Add AstraDB RAG Flow guide
* Remove unused imports
* Remove unnecessary import statement
* Refactor guide for better readability
* Add data component documentation
* Update component headings and add prompt template
* Fix logging level and version display
* Add datetime import and buffer for alembic log
* Update flow names in NewFlowModal and documentation
* Add starter projects to sidebars.js
* Fix error handling in DirectoryReader class
* Handle exception when loading components in setup.py
* Update version numbers in pyproject.toml files
* Update build_langflow_base and build_langflow_backup in Makefile
* Added docs
* Update dependencies and build process
* Add Admonition component for API Key documentation
* Update API endpoint in async-api.mdx
* Remove async-api guidelines
* Fix UnicodeDecodeError in DirectoryReader
* Update dependency version and fix encoding issues
* Add conditional build and publish for base and main projects
* Update version to 1.0.0a2 in pyproject.toml
* Remove duplicate imports and unnecessary code in custom-component.mdx
* Fix poetry lock command in Makefile
* Update package versions in pyproject.toml
* Remove unused components and update imports
* 📦 chore(pre-release-base.yml): add pre-release workflow for base project
📦 chore(pre-release-langflow.yml): add pre-release workflow for langflow project
* Add ChatLiteLLMModelComponent to models package
* Add frontend installation and build steps
* Add Dockerfile for building and pushing base image
* Add emoji package and nest-asyncio dependency
* 📝 (components.mdx): update margin style of ZoomableImage to improve spacing
📝 (features.mdx): update margin style of ZoomableImage to improve spacing
📝 (login.mdx): update margin style of ZoomableImage to improve spacing
* Fix module import error in validate.py
* Fix error message in directory_reader.py
* Update version import and handle ImportError
* Add cryptography and langchain-openai dependencies
* Update poetry installation and remove poetry-monorepo-dependency-plugin
* Update workflow and Dockerfile for Langflow base pre-release
* Update display names and descriptions for AstraDB components
* Update installation instructions for Langflow
* Update Astra DB links and remove unnecessary imports
* Rename AstraDB
* Add new components and images
* Update HuggingFace Spaces URLs
* Update Langflow documentation and add new starter projects
* Update flow name to "Basic Prompting (Hello, world!)" in relevant files
* Update Basic Prompting flow name to "Ahoy World!"
* Remove HuggingFace Spaces documentation
* Add new files and update sidebars.js
* Remove async-tasks.mdx and update sidebars.js
* Update starter project URLs
* Enable migration of global variables
* Update OpenAIEmbeddings deployment and model
* 📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (inputs.mdx): add margin to image style to improve spacing and center alignment
📝 (rag-with-astradb.mdx): add margin to image styles to improve spacing and readability
* Update welcome message in index.mdx
* Add global variable feature to Langflow documentation
* Reorganized sidebar categories
* Update migration documentation
* Refactor SplitTextComponent class to accept inputs of type Record and Text
* Adjust embeddings docs
* ✨ (cardComponent/index.tsx): add a minimum height to the card component to ensure consistent layout and prevent content from overlapping when the card is empty or has minimal content
* Update flow name from "Ahoy World!" to "Hello, world!"
* Update documentation for embeddings, models, and vector stores
* Update CreateRecordComponent and parameterUtils.ts
* Add documentation for Text and Record types
* Remove commented lines in sidebars.js
* Add run_flow_from_json function to load.py
* Update Langflow package to run flow from JSON file
* Fix type annotations and import errors
* Refactor tests and fix test data
---------
Co-authored-by: Rodrigo Nader <rodrigosilvanader@gmail.com>
Co-authored-by: anovazzi1 <otavio2204@gmail.com>
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
Co-authored-by: carlosrcoelho <carlosrodrigo.coelho@gmail.com>
Co-authored-by: cristhianzl <cristhian.lousa@gmail.com>
Co-authored-by: Matheus <jacquesmats@gmail.com>
This commit is contained in:
Gabriel Luiz Freitas Almeida
GitHub
parent
20f640c4ce
commit
05cd6e4fd7
853 changed files with 59936 additions and 15456 deletions
0
docs/docs/migration/api.mdx
Normal file
0
docs/docs/migration/api.mdx
Normal file
44
docs/docs/migration/compatibility.mdx
Normal file
44
docs/docs/migration/compatibility.mdx
Normal file
|
|
@ -0,0 +1,44 @@
|
|||
import Admonition from '@theme/Admonition';
|
||||
|
||||
# Compatibility with Previous Versions
|
||||
|
||||
|
||||
## TLDR;
|
||||
|
||||
- You'll need to add a few components to your flow to make it compatible with the new version of Langflow.
|
||||
- Add a Runnable Executor, connect it to the last component (a Chain or an Agent) in your flow, and connect a Chat Input and a Chat Output to the Runnable Executor. This should work *most of the time*.
|
||||
- You might also need to update the Chain or Agent component to the latest version.
|
||||
- Most Components will work as they are, but you'll need to add an Input and an Output to your flow.
|
||||
- You can use the Runnable Executor to run a LangChain runnable (which is the output of many components before 1.0)
|
||||
- We need your feedback on this, so please let us know how it goes and what you think.
|
||||
|
||||
## Introduction
|
||||
|
||||
Langflow now works best with a flow that has an Input and an Output and that is mostly what you'll need to add to your existing flows.
|
||||
|
||||
Hopefully, you'll find that even though you still can work with your current flows, updating all your components to the new version of Langflow will be worth it.
|
||||
|
||||
We've tried to make it as easy as possible for you to adapt your existing flows to work seamlessly in the new version of Langflow.
|
||||
|
||||
## How to Adapt Your Existing Flows
|
||||
|
||||
|
||||
The steps to take are few but not always simple. Here's how you can adapt your existing flows to work seamlessly in the new version of Langflow:
|
||||
|
||||
<Admonition type="caution">
|
||||
<p>**Caution:**</p>
|
||||
<p>While this should work most of the time, it might not work for all flows. You might need to update the Chain or Agent component to the latest version. Please let us know if you encounter any issues.</p>
|
||||
</Admonition>
|
||||
|
||||
1. **Check if your flow ends with a Chain or Agent component**.
|
||||
- If it does not, it *should* work as it is because it probably was not a chat flow.
|
||||
2. **Add a Runnable Executor**.
|
||||
- Add a Runnable Executor to the end of your flow.
|
||||
- Connect the last component (a Chain or an Agent) in your flow to the Runnable Executor.
|
||||
3. **Add a Chat Input and a Chat Output**.
|
||||
- Add a Chat Input and a Chat Output to your flow.
|
||||
- Connect the Chat Input to the Runnable Executor.
|
||||
- Connect the Chat Output to the Runnable Executor.
|
||||
|
||||
{/* Add picture of the flow */}
|
||||
|
||||
0
docs/docs/migration/connecting-output-components.mdx
Normal file
0
docs/docs/migration/connecting-output-components.mdx
Normal file
0
docs/docs/migration/custom-component.mdx
Normal file
0
docs/docs/migration/custom-component.mdx
Normal file
0
docs/docs/migration/experimental-components.mdx
Normal file
0
docs/docs/migration/experimental-components.mdx
Normal file
0
docs/docs/migration/flow-of-data.mdx
Normal file
0
docs/docs/migration/flow-of-data.mdx
Normal file
65
docs/docs/migration/global-variables.mdx
Normal file
65
docs/docs/migration/global-variables.mdx
Normal file
|
|
@ -0,0 +1,65 @@
|
|||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# Global Variables
|
||||
|
||||
Global Variables are a really useful feature of Langflow.
|
||||
They allow you to define reusable variables that can be accessed from any Text field in your project.
|
||||
|
||||
The first thing you need to do is find a **Text field** in a Component, so let's talk about what a Text field is.
|
||||
|
||||
## Text Fields
|
||||
|
||||
Text fields are the fields in a Component where you can write text but that does not allow you to open a Text Area.
|
||||
|
||||
The easiest way to find fields that are Text fields, though, is to look for fields that have a 🌐 button.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/ollama-gv.png",
|
||||
dark: "img/ollama-gv.png",
|
||||
}}
|
||||
style={{ width: "50%" }}
|
||||
/>
|
||||
|
||||
## Creating a Global Variable
|
||||
|
||||
To create a Global Variable, you need to click on the 🌐 button in a Text field and that will open a dropdown showing your currently available variables and at the end of it **+ Add New Variable**.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/add-new-variable.png",
|
||||
dark: "img/add-new-variable.png",
|
||||
}}
|
||||
style={{ width: "60%" }}
|
||||
/>
|
||||
|
||||
Click on **+ Add New Variable** and a window will open where you can define your new Global Variable.
|
||||
|
||||
In it, you can define the **Name** of the variable, the optional **Type** of the variable, and the **Value** of the variable.
|
||||
|
||||
The **Name** is the name that you will use to refer to the variable in your Text fields.
|
||||
|
||||
The **Type** is optional for now but will be used in the future to allow for more advanced features.
|
||||
|
||||
The **Value** is the value that the variable will have.
|
||||
{/* say that all variables are encrypted */}
|
||||
|
||||
<Admonition type="warning">
|
||||
All Global Variables are encrypted and cannot be accessed by anyone but you.
|
||||
</Admonition>
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/create-variable-window.png",
|
||||
dark: "img/create-variable-window.png",
|
||||
}}
|
||||
style={{ width: "60%" }}
|
||||
/>
|
||||
|
||||
After you have defined your variable, click on **Save Variable** and your variable will be created.
|
||||
|
||||
After that, once you click on the 🌐 button in a Text field, you will see your new variable in the dropdown.
|
||||
36
docs/docs/migration/inputs-and-outputs.mdx
Normal file
36
docs/docs/migration/inputs-and-outputs.mdx
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
# Inputs and Outputs
|
||||
|
||||
TL;DR: Inputs and Outputs are a category of components that are used to define where data comes in and out of your flow. They also
|
||||
dynamically change the Interaction Panel and can be renamed to make it easier to build and maintain your flows.
|
||||
|
||||
## Introduction
|
||||
|
||||
Langflow 1.0 introduces new categories of components called Inputs and Outputs. They are used to make it easier to understand and interact with your flows.
|
||||
|
||||
Let's start with what they have in common:
|
||||
|
||||
- Components in these categories connect to components that have Text or Record inputs or outputs. Some can connect to both but you have to pick what type of data you want to output or input.
|
||||
- They can be renamed to help you identify them more easily in the Interaction Panel and while using the API.
|
||||
- They dynamically change the Interaction Panel to make it easier to understand and interact with your flows.
|
||||
|
||||
Native Langflow Components were created to be powerful tools that work around Langflow's features. They are designed to be easy to use and understand, and to help you build your flows faster.
|
||||
|
||||
Let's dive into Inputs and Outputs.
|
||||
|
||||
## Inputs
|
||||
|
||||
Inputs are components that are used to define where data comes into your flow. They can be used to receive data from the user, from a database, or from any other source that can be converted to Text or Record.
|
||||
|
||||
The difference between Chat Input and other Input components is the format of the output, the number of configurable fields, and the way they are displayed in the Interaction Panel.
|
||||
|
||||
Chat Input components can output Text or Record. When you want to pass the sender name, or sender to the next component, you can use the Record output, and when you want to pass the message only you can use the Text output. This is useful when saving the message to a database or a memory system like Zep.
|
||||
|
||||
You can find out more about it and the other Inputs [here](../components/inputs).
|
||||
|
||||
## Outputs
|
||||
|
||||
Outputs are components that are used to define where data comes out of your flow. They can be used to send data to the user, to the Interaction Panel, or to define how the data will be displayed in the Interaction Panel.
|
||||
|
||||
The Chat Output works similarly to the Chat Input but does not have a field that allows for written input. It is used as an Output definition and can be used to send data to the user.
|
||||
|
||||
You can find out more about it and the other Outputs [here](../components/outputs).
|
||||
0
docs/docs/migration/multiple-flows.mdx
Normal file
0
docs/docs/migration/multiple-flows.mdx
Normal file
0
docs/docs/migration/new-categories-and-components.mdx
Normal file
0
docs/docs/migration/new-categories-and-components.mdx
Normal file
0
docs/docs/migration/passing-tweaks-and-inputs.mdx
Normal file
0
docs/docs/migration/passing-tweaks-and-inputs.mdx
Normal file
0
docs/docs/migration/renaming-and-editing-components.mdx
Normal file
0
docs/docs/migration/renaming-and-editing-components.mdx
Normal file
0
docs/docs/migration/sidebar-and-interaction-panel.mdx
Normal file
0
docs/docs/migration/sidebar-and-interaction-panel.mdx
Normal file
0
docs/docs/migration/state-management.mdx
Normal file
0
docs/docs/migration/state-management.mdx
Normal file
0
docs/docs/migration/supported-frameworks.mdx
Normal file
0
docs/docs/migration/supported-frameworks.mdx
Normal file
45
docs/docs/migration/text-and-record.mdx
Normal file
45
docs/docs/migration/text-and-record.mdx
Normal file
|
|
@ -0,0 +1,45 @@
|
|||
# Text and Record
|
||||
|
||||
In Langflow 1.0 we added two main input and output types: Text and Record. Text is a simple string input and output type, while Record is a structure very similar to a dictionary in Python. It is a key-value pair data structure.
|
||||
|
||||
We've created a few components to help you work with these types. Let's see how a few of them work.
|
||||
|
||||
### Records To Text
|
||||
|
||||
This is a Component that takes in Records and outputs a Text. It does this using a template string and concatenating the values of the Record, one per line.
|
||||
|
||||
If we have the following Records:
|
||||
|
||||
```json
|
||||
{
|
||||
"sender_name": "Alice",
|
||||
"message": "Hello!"
|
||||
}
|
||||
{
|
||||
"sender_name": "John",
|
||||
"message": "Hi!"
|
||||
}
|
||||
```
|
||||
|
||||
And the template string is: _`{sender_name}: {message}`_
|
||||
|
||||
```
|
||||
Alice: Hello!
|
||||
John: Hi!
|
||||
```
|
||||
|
||||
### Create Record
|
||||
|
||||
This Component allows you to create a Record from a number of inputs. You can add as many key-value pairs as you want (as long as it is less than 15 😅). Once you've picked that number you'll need to write the name of the Key and can pass Text values from other components to it.
|
||||
|
||||
### Documents To Records
|
||||
|
||||
This Component takes in a [LangChain](https://langchain.com) Document and outputs a Record. It does this by extracting the _`page_content`_ and the _`metadata`_ from the Document and adding them to the Record as _`text`_ and _`data`_ respectively.
|
||||
|
||||
## Why is this useful?
|
||||
|
||||
The idea was to create a unified way to work with complex data in Langflow, and to make it easier to work with data that is not just a simple string. This way you can create more complex workflows and use the data in more ways.
|
||||
|
||||
## What's next?
|
||||
|
||||
We are planning to integrate an array of modalities to Langflow, such as images, audio, and video. This will allow you to create even more complex workflows and use cases. Stay tuned for more updates! 🚀
|
||||
Loading…
Add table
Add a link
Reference in a new issue