merge dev on playground
This commit is contained in:
cristhianzl
commit
101a045cba
90 changed files with 1802 additions and 1114 deletions
|
|
@ -12,7 +12,7 @@ To use a custom component, follow these steps:
|
|||
|
||||
<Admonition type="info" label="Tip">
|
||||
|
||||
For an in-depth explanation of custom components, their rules, and applications, make sure to read [Custom Component guidelines](../guidelines/custom-component).
|
||||
For an in-depth explanation of custom components, their rules, and applications, make sure to read [Custom Component guidelines](../administration/custom-component).
|
||||
|
||||
</Admonition>
|
||||
|
||||
|
|
@ -57,7 +57,7 @@ The CustomComponent class serves as the foundation for creating custom component
|
|||
|
||||
<Admonition type="info">
|
||||
Unlike Langchain types, base Python types do not add a
|
||||
[handle](../guidelines/components) to the field by default. To add handles,
|
||||
[handle](../administration/components) to the field by default. To add handles,
|
||||
use the _`input_types`_ key in the _`build_config`_ method.
|
||||
</Admonition>
|
||||
|
||||
|
|
|
|||
|
|
@ -21,7 +21,7 @@ The `PromptTemplate` component allows users to create prompts and define variabl
|
|||
<Admonition type="info">
|
||||
Once a variable is defined in the prompt template, it becomes a component
|
||||
input of its own. Check out [Prompt
|
||||
Customization](../guidelines/prompt-customization) to learn more.
|
||||
Customization](../administration/prompt-customization) to learn more.
|
||||
</Admonition>
|
||||
|
||||
- **template:** Template used to format an individual request.
|
||||
|
|
|
|||
|
|
@ -159,7 +159,7 @@ Now, let's add the [parameters](focus://11[20:55]) and the [return type](focus:/
|
|||
|
||||
- _`flow_name`_ is the name of the flow we want to run.
|
||||
- _`document`_ is the input document to be passed to that flow.
|
||||
- Since _`Document`_ is a Langchain type, it will add an input [handle](../guidelines/components) to the component ([see more](../components/custom)).
|
||||
- Since _`Document`_ is a Langchain type, it will add an input [handle](../administration/components) to the component ([see more](../components/custom)).
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -242,7 +242,7 @@ class FlowRunner(CustomComponent):
|
|||
|
||||
```
|
||||
|
||||
You can load this flow using _`get_flow`_ and set a _`tweaks`_ dictionary to customize it. Find more about tweaks in our [features guidelines](../guidelines/features#code).
|
||||
You can load this flow using _`get_flow`_ and set a _`tweaks`_ dictionary to customize it. Find more about tweaks in our [features guidelines](../administration/features#code).
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
27
docs/docs/getting-started/huggingface-spaces.mdx
Normal file
27
docs/docs/getting-started/huggingface-spaces.mdx
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# 🤗 HuggingFace Spaces
|
||||
|
||||
Hugging Face provides a great alternative for running Langflow in their Spaces environment. This means you can run Langflow without any local installation required.
|
||||
|
||||
The first step is to go to the [Langflow Space](https://huggingface.co/spaces/Langflow/Langflow?duplicate=true) or [Langflow 1.0 Preview Space](https://huggingface.co/spaces/Langflow/Langflow-Preview?duplicate=true)
|
||||
|
||||
Remember to use a Chromium-based browser for the best experience. You'll be presented with the following screen:
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/duplicate-space.png",
|
||||
dark: "img/duplicate-space.png",
|
||||
}}
|
||||
style={{ width: "100%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
From here, just name your Space, define the visibility (Public or Private), and click on `Duplicate Space` to start the installation process. When that is done, you'll be redirected to the Space's main page to start using Langflow right away!
|
||||
|
||||
Once you get Langflow running, click on New Project in the top right corner of the screen. Langflow provides a range of example flows to help you get started.
|
||||
|
||||
To quickly try one of them, open a starter example, set up your API keys and click ⚡ Run, on the bottom right corner of the canvas. This will open up Langflow's Interaction Panel with the chat console, text inputs, and outputs.
|
||||
77
docs/docs/getting-started/install-langflow.mdx
Normal file
77
docs/docs/getting-started/install-langflow.mdx
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# 📦 Install Langflow
|
||||
|
||||
<Admonition type="info">
|
||||
Langflow v1.0 is also available in a [HuggingFace Preview Space](https://huggingface.co/spaces/Langflow/Langflow-Preview?duplicate=true) if you'd rather try it out before installing locally.
|
||||
</Admonition>
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Langflow requires the following programs installed on your system.
|
||||
|
||||
* [Python 3.10](https://www.python.org/downloads/release/python-3100/)
|
||||
|
||||
* [pip](https://pypi.org/project/pip/) or [pipx](https://pipx.pypa.io/stable/installation/)
|
||||
|
||||
## Install Langflow
|
||||
|
||||
To install Langflow:
|
||||
|
||||
pip:
|
||||
```bash
|
||||
python -m pip install langflow -U
|
||||
```
|
||||
|
||||
pipx:
|
||||
```bash
|
||||
pipx install langflow --python python3.10 --fetch-missing-python
|
||||
```
|
||||
Pipx can fetch the missing Python version for you with `--fetch-missing-python`, but you can also install the Python version manually.
|
||||
|
||||
|
||||
## Install Langflow pre-release
|
||||
|
||||
Use `--force-reinstall` to ensure you have the latest version of Langflow and its dependencies.
|
||||
|
||||
To install a pre-release version of Langflow:
|
||||
|
||||
pip:
|
||||
```bash
|
||||
python -m pip install langflow --pre --force-reinstall
|
||||
```
|
||||
|
||||
pipx:
|
||||
```bash
|
||||
pipx install langflow --python python3.10 --fetch-missing-python --pip-args="--pre --force-reinstall"
|
||||
```
|
||||
|
||||
## Having a problem?
|
||||
|
||||
If you encounter a problem, see [Possible Installation Issues](/migration/possible-installation-issues).
|
||||
|
||||
To get help in the Langflow CLI:
|
||||
|
||||
```bash
|
||||
python -m langflow --help
|
||||
```
|
||||
|
||||
## ⛓️ Run Langflow
|
||||
|
||||
1. To run Langflow, enter the following command.
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
2. Confirm that a local Langflow instance starts by visiting `http://127.0.0.1:7860` in your browser.
|
||||
```bash
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
3. Continue on to the [Quickstart](./quickstart.mdx).
|
||||
10
docs/docs/getting-started/new-to-llms.mdx
Normal file
10
docs/docs/getting-started/new-to-llms.mdx
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
# 📚 New to LLMs?
|
||||
|
||||
Large Language Models, or LLMs, are part of an exciting new world in computing.
|
||||
|
||||
We made Langflow for anyone to create with LLMs, and hope you'll feel comfortable installing Langflow and [getting started](./quickstart.mdx).
|
||||
|
||||
If you want to learn more about LLMs, prompt engineering, and AI models, Langflow recommends [promptingguide.ai](https://promptingguide.ai), an open-source repository of prompt engineering content maintained by AI experts.
|
||||
PromptingGuide offers content for [beginners](https://www.promptingguide.ai/introduction/basics) and [experts](https://www.promptingguide.ai/techniques/cot), as well as the latest [research papers](https://www.promptingguide.ai/papers) and [test results](https://www.promptingguide.ai/research) fueling AI's progress.
|
||||
|
||||
Wherever you are on your AI journey, it's helpful to keep Prompting Guide open in a tab.
|
||||
119
docs/docs/getting-started/quickstart.mdx
Normal file
119
docs/docs/getting-started/quickstart.mdx
Normal file
|
|
@ -0,0 +1,119 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import ReactPlayer from "react-player";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# ⚡️ Quickstart
|
||||
|
||||
This quickstart demonstrates how to install Langflow, run it locally, build a basic prompt flow, and modify that prompt for different outcomes.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
* [Python 3.10](https://www.python.org/downloads/release/python-3100/)
|
||||
|
||||
* [pip](https://pypi.org/project/pip/) or [pipx](https://pipx.pypa.io/stable/installation/)
|
||||
|
||||
* [OpenAI API key](https://platform.openai.com)
|
||||
|
||||
## Install Langflow
|
||||
|
||||
<Admonition type="info">
|
||||
Langflow v1.0 is also available in a [HuggingFace Preview Space](https://huggingface.co/spaces/Langflow/Langflow-Preview?duplicate=true) if you'd rather try it out before installing locally. This quickstart will run there, too.
|
||||
</Admonition>
|
||||
|
||||
1. To install Langflow, enter the following command in pip or pipx:
|
||||
|
||||
pip:
|
||||
```bash
|
||||
python -m pip install langflow -U
|
||||
```
|
||||
|
||||
pipx:
|
||||
```bash
|
||||
pipx install langflow --python python3.10 --fetch-missing-python
|
||||
```
|
||||
Pipx can fetch the missing Python version for you with `--fetch-missing-python`, but you can also install the Python version manually.
|
||||
|
||||
2. Start a local Langflow instance with the Langflow CLI:
|
||||
```bash
|
||||
langflow run
|
||||
```
|
||||
|
||||
Or start Langflow with Python:
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
Result:
|
||||
```
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
3. Go to `http://127.0.0.1:7860` and confirm the Langflow UI is available.
|
||||
|
||||
<Admonition type="info">
|
||||
If you encounter a problem, see [Possible Installation Issues](/migration/possible-installation-issues).
|
||||
</Admonition>
|
||||
|
||||
## Create the basic prompting project
|
||||
|
||||
Now that you have Langflow installed and running, let us formally welcome you to Langflow!👋
|
||||
|
||||
You will use Langflow's prompt tools to issue prompts to the OpenAI LLM.
|
||||
|
||||
Prompts serve as the inputs to a large language model (LLM), acting as the interface between human instructions and computational tasks.
|
||||
|
||||
By submitting natural language requests in a prompt to an LLM, you can obtain answers, generate text, and solve problems.
|
||||
|
||||
1. From the Langflow dashboard, click **New Project**.
|
||||
2. Select **Basic Prompting**.
|
||||
3. The **Basic Prompting** flow is created.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/quickstart.png",
|
||||
dark: "img/quickstart.png",
|
||||
}}
|
||||
style={{ width: "80%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
This flow allows you to chat with the **OpenAI** component via a **Prompt** component.
|
||||
Examine the **Prompt** component. The **Template** field instructs the LLM to `Answer the user as if you were a pirate.`
|
||||
This should be interesting...
|
||||
|
||||
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
1. In the **Variable Name** field, enter `openai_api_key`.
|
||||
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
|
||||
3. Click **Save Variable**.
|
||||
|
||||
## Run the basic prompting flow
|
||||
|
||||
1. Click the **Run** button.
|
||||
The **Interaction Panel** opens, where you can converse with your bot.
|
||||
2. Type a message and press Enter.
|
||||
The bot responds in a markedly piratical manner!
|
||||
|
||||
## Modify the prompt for a different result
|
||||
|
||||
1. To modify your prompt results, in the **Prompt** template, click the **Template** field.
|
||||
The **Edit Prompt** window opens.
|
||||
2. Change `Answer the user as if you were a pirate` to a different character, perhaps `Answer the user as if you were Harold Abelson.`
|
||||
3. Run the basic prompting flow again.
|
||||
The response will be markedly different.
|
||||
|
||||
## Next steps
|
||||
|
||||
Well done! You've built your first prompt in Langflow. 🎉
|
||||
|
||||
By adding Langflow components to this prompt, you can build all sorts of interesting flows.
|
||||
|
||||
* [Memory chatbot](/starter-projects/memory-chatbot.mdx)
|
||||
* [Blog writer](/starter-projects/blog-writer.mdx)
|
||||
* [Document QA](/starter-projects/document-qa.mdx)
|
||||
|
||||
|
||||
|
|
@ -5,7 +5,9 @@ import Admonition from "@theme/Admonition";
|
|||
|
||||
# 👋 Welcome to Langflow
|
||||
|
||||
Langflow is an easy way to build from simple to complex AI applications. It is a low-code platform that allows you to integrate AI into everything you do.
|
||||
Langflow is a low-code platform that allows you to integrate AI into everything you do.
|
||||
|
||||
Use Langflow's simple but powerful UI to build any AI application you can dream up, from simple to complex.
|
||||
|
||||
{" "}
|
||||
|
||||
|
|
@ -20,96 +22,17 @@ Langflow is an easy way to build from simple to complex AI applications. It is a
|
|||
|
||||
## 🚀 First steps
|
||||
|
||||
## Installation
|
||||
- [Install Langflow](/getting-started/install-langflow) - Install and start a local Langflow server.
|
||||
|
||||
Make sure you have **Python 3.10** installed on your system.
|
||||
- [Quickstart](/getting-started/quickstart) - Install Langflow, create a flow, and run it.
|
||||
|
||||
You can install **Langflow** with [pipx](https://pipx.pypa.io/stable/installation/) or with pip.
|
||||
- [HuggingFace Spaces](/getting-started/huggingface-spaces) - Duplicate the Langflow preview space and try it out before you install.
|
||||
|
||||
Pipx can fetch the missing Python version for you, but you can also install it manually.
|
||||
- [New to LLMs?](/getting-started/new-to-llms) - Learn more about LLMs, prompting, and more at [promptingguide.ai](https://promptingguide.ai).
|
||||
|
||||
```bash
|
||||
# Remember to check if you have Python 3.10 installed
|
||||
python -m pip install langflow -U
|
||||
# or
|
||||
pipx install langflow --python python3.10 --fetch-missing-python
|
||||
```
|
||||
## Learn more about Langflow 1.0
|
||||
|
||||
Or you can install a pre-release version using:
|
||||
Learn more about the exciting changes in Langflow 1.0, and how to migrate your existing Langflow projects.
|
||||
|
||||
```bash
|
||||
python -m pip install langflow --pre --force-reinstall
|
||||
# or
|
||||
pipx install langflow --python python3.10 --fetch-missing-python --pip-args="--pre --force-reinstall"
|
||||
```
|
||||
|
||||
<Admonition type="tip">
|
||||
<p>
|
||||
Please, check out our [Possible Installation Issues
|
||||
section](/migration/possible-installation-issues) if you encounter any
|
||||
problems.
|
||||
</p>
|
||||
</Admonition>
|
||||
|
||||
We recommend using --force-reinstall to ensure you have the latest version of Langflow and its dependencies.
|
||||
|
||||
### ⛓️ Running Langflow
|
||||
|
||||
Langflow can be run in a variety of ways, including using the command-line interface (CLI) or HuggingFace Spaces.
|
||||
|
||||
```bash
|
||||
python -m langflow run # or langflow --help
|
||||
```
|
||||
|
||||
#### 🤗 HuggingFace Spaces
|
||||
|
||||
Hugging Face provides a great alternative for running Langflow in their Spaces environment. This means you can run Langflow without any local installation required.
|
||||
|
||||
The first step is to go to the [Langflow Space](https://huggingface.co/spaces/Langflow/Langflow?duplicate=true) or [Langflow 1.0 Preview Space](https://huggingface.co/spaces/Langflow/Langflow-Preview?duplicate=true)
|
||||
|
||||
Remember to use a Chromium-based browser for the best experience. You'll be presented with the following screen:
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/duplicate-space.png",
|
||||
dark: "img/duplicate-space.png",
|
||||
}}
|
||||
style={{ width: "100%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
From here, just name your Space, define the visibility (Public or Private), and click on `Duplicate Space` to start the installation process. When that is done, you'll be redirected to the Space's main page to start using Langflow right away!
|
||||
|
||||
Once you get Langflow running, click on New Project in the top right corner of the screen. Langflow provides a range of example flows to help you get started.
|
||||
|
||||
To quickly try one of them, open a starter example, set up your API keys and click ⚡ Run, on the bottom right corner of the canvas. This will open up Langflow's Playground with the chat console, text inputs, and outputs.
|
||||
|
||||
### 🖥️ 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:
|
||||
|
||||
```bash
|
||||
langflow run [OPTIONS]
|
||||
```
|
||||
|
||||
Find more information about the available options by running:
|
||||
|
||||
```bash
|
||||
python -m langflow --help
|
||||
```
|
||||
|
||||
## Find out more about 1.0
|
||||
|
||||
<Admonition type="caution" icon="🚧" title="ZONE UNDER CONSTRUCTION">
|
||||
<p>
|
||||
We are currently working on updating the documentation for Langflow 1.0.
|
||||
</p>
|
||||
</Admonition>
|
||||
|
||||
To get you learning more about what's new and why you should be excited about Langflow 1.0,
|
||||
go to [A new chapter for Langflow](/whats-new/a-new-chapter-langflow) and also come back often
|
||||
to check out our [migration guides](/whats-new/migrating-to-one-point-zero) as we release them.
|
||||
- [A new chapter for Langflow](/whats-new/a-new-chapter-langflow)
|
||||
- [Migration guides](/migration/migrating-to-one-point-zero)
|
||||
|
|
|
|||
|
|
@ -25,3 +25,16 @@ For this error to occur, two scenarios are possible:
|
|||
In this case, you might not be running the correct executable.
|
||||
To solve this issue, you can run the correct executable by running _`python -m langflow run`_ instead of _`langflow run`_ and if that doesn't work, you can try uninstalling langflow and reinstalling it using _`python -m pip install langflow --pre -U`_.
|
||||
2. Some version conflicts might have occurred during the installation process. Run _`python -m pip install langflow --pre -U --force-reinstall`_ to reinstall langflow and its dependencies.
|
||||
|
||||
## _`Something went wrong running migrations. Please, run 'langflow migration --fix'`_
|
||||
|
||||
TLDR;
|
||||
|
||||
- Clear the cache by deleting the contents of the cache folder.
|
||||
This folder can be found at:
|
||||
- **Linux or WSL2 on Windows**: `home/<username>/.cache/langflow/`
|
||||
- **MacOS**: `/Users/<username>/Library/Caches/langflow/`
|
||||
|
||||
If you wish to retain your files, ensure to back them up before clearing the folder.
|
||||
|
||||
This error often occurs when upgrading Langflow, the new version can't override `langflow-pre.db` in `.cache/langflow/`. Clearing the cache removes this file but will also erase your settings.
|
||||
83
docs/docs/starter-projects/basic-prompting.mdx
Normal file
83
docs/docs/starter-projects/basic-prompting.mdx
Normal file
|
|
@ -0,0 +1,83 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import ReactPlayer from "react-player";
|
||||
|
||||
# Basic prompting
|
||||
|
||||
Prompts serve as the inputs to a large language model (LLM), acting as the interface between human instructions and computational tasks.
|
||||
|
||||
By submitting natural language requests in a prompt to an LLM, you can obtain answers, generate text, and solve problems.
|
||||
|
||||
This article demonstrates how to use Langflow's prompt tools to issue basic prompts to an LLM, and how various prompting strategies can affect your outcomes.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Install Langflow.
|
||||
```bash
|
||||
python -m pip install langflow --pre
|
||||
```
|
||||
|
||||
2. Start a local Langflow instance with the Langflow CLI:
|
||||
```bash
|
||||
langflow run
|
||||
```
|
||||
Or start Langflow with Python:
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
Result:
|
||||
```
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
Alternatively, go to [HuggingFace Spaces](https://docs.langflow.org/getting-started/hugging-face-spaces) or [Lightning.ai Studio](https://lightning.ai/ogabrielluiz-8j6t8/studios/langflow) for a pre-built Langflow test environment.
|
||||
|
||||
3. Create an [OpenAI API key](https://platform.openai.com).
|
||||
|
||||
## Create the basic prompting project
|
||||
|
||||
1. From the Langflow dashboard, click **New Project**.
|
||||
2. Select **Basic Prompting**.
|
||||
3. The **Basic Prompting** flow is created.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/basic-prompting.png",
|
||||
dark: "img/basic-prompting.png",
|
||||
}}
|
||||
style={{ width: "80%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
This flow allows you to chat with the **OpenAI** component via a **Prompt** component.
|
||||
Examine the **Prompt** component. The **Template** field instructs the LLM to `Answer the user as if you were a pirate.`
|
||||
This should be interesting...
|
||||
|
||||
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
1. In the **Variable Name** field, enter `openai_api_key`.
|
||||
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
|
||||
3. Click **Save Variable**.
|
||||
|
||||
## Run the basic prompting flow
|
||||
|
||||
1. Click the **Run** button.
|
||||
The **Interaction Panel** opens, where you can converse with your bot.
|
||||
2. Type a message and press Enter.
|
||||
The bot responds in a markedly piratical manner!
|
||||
|
||||
## Modify the prompt for a different result
|
||||
|
||||
1. To modify your prompt results, in the **Prompt** template, click the **Template** field.
|
||||
The **Edit Prompt** window opens.
|
||||
2. Change `Answer the user as if you were a pirate` to a different character, perhaps `Answer the user as if you were Harold Abelson.`
|
||||
3. Run the basic prompting flow again.
|
||||
The response will be markedly different.
|
||||
|
||||
|
||||
|
||||
|
||||
92
docs/docs/starter-projects/blog-writer.mdx
Normal file
92
docs/docs/starter-projects/blog-writer.mdx
Normal file
|
|
@ -0,0 +1,92 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import ReactPlayer from "react-player";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# Blog writer
|
||||
|
||||
Build a blog writer with OpenAI that uses URLs for reference content.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Install Langflow.
|
||||
```bash
|
||||
python -m pip install langflow --pre
|
||||
```
|
||||
|
||||
2. Start a local Langflow instance with the Langflow CLI:
|
||||
```bash
|
||||
langflow run
|
||||
```
|
||||
Or start Langflow with Python:
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
Result:
|
||||
```bash
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
Alternatively, go to [HuggingFace Spaces](https://docs.langflow.org/getting-started/hugging-face-spaces) or [Lightning.ai Studio](https://lightning.ai/ogabrielluiz-8j6t8/studios/langflow) for a pre-built Langflow test environment.
|
||||
|
||||
3. Create an [OpenAI API key](https://platform.openai.com).
|
||||
|
||||
## Create the Blog Writer project
|
||||
|
||||
1. From the Langflow dashboard, click **New Project**.
|
||||
2. Select **Blog Writer**.
|
||||
3. The **Blog Writer** flow is created.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/blog-writer.png",
|
||||
dark: "img/blog-writer.png",
|
||||
}}
|
||||
style={{ width: "80%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
This flow creates a one-shot prompt flow with **Prompt**, **OpenAI**, and **Chat Output** components, and augments the flow with reference content and instructions from the **URL** and **Instructions** components.
|
||||
|
||||
The **Prompt** component's default **Template** field looks like this:
|
||||
```bash
|
||||
Reference 1:
|
||||
|
||||
{reference_1}
|
||||
|
||||
---
|
||||
|
||||
Reference 2:
|
||||
|
||||
{reference_2}
|
||||
|
||||
---
|
||||
|
||||
{instructions}
|
||||
|
||||
Blog:
|
||||
|
||||
```
|
||||
|
||||
The `{instructions}` value is received from the **Value** field of the **Instructions** component.
|
||||
The `reference_1` and `reference_2` values are received from the **URL** fields of the **URL** components.
|
||||
|
||||
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
1. In the **Variable Name** field, enter `openai_api_key`.
|
||||
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
|
||||
3. Click **Save Variable**.
|
||||
|
||||
## Run the Blog Writer flow
|
||||
|
||||
1. Click the **Run** button.
|
||||
The **Interaction Panel** opens, where you can run your one-shot flow.
|
||||
2. Click the **Lighting Bolt** icon to run your flow.
|
||||
3. The **OpenAI** component constructs a blog post with the **URL** items as context.
|
||||
The default **URL** values are for web pages at `promptingguide.ai`, so your blog post will be about prompting LLMs.
|
||||
|
||||
To write about something different, change the values in the **URL** components, and see what the LLM constructs.
|
||||
82
docs/docs/starter-projects/document-qa.mdx
Normal file
82
docs/docs/starter-projects/document-qa.mdx
Normal file
|
|
@ -0,0 +1,82 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import ReactPlayer from "react-player";
|
||||
import Admonition from "@theme/Admonition";
|
||||
|
||||
# Document QA
|
||||
|
||||
Build a question-and-answer chatbot with a document loaded from local memory.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Install Langflow.
|
||||
```bash
|
||||
python -m pip install langflow --pre
|
||||
```
|
||||
|
||||
2. Start a local Langflow instance with the Langflow CLI:
|
||||
```bash
|
||||
langflow run
|
||||
```
|
||||
Or start Langflow with Python:
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
Result:
|
||||
```
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
Alternatively, go to [HuggingFace Spaces](https://docs.langflow.org/getting-started/hugging-face-spaces) or [Lightning.ai Studio](https://lightning.ai/ogabrielluiz-8j6t8/studios/langflow) for a pre-built Langflow test environment.
|
||||
|
||||
3. Create an [OpenAI API key](https://platform.openai.com).
|
||||
|
||||
## Create the Document QA project
|
||||
|
||||
1. From the Langflow dashboard, click **New Project**.
|
||||
2. Select **Document QA**.
|
||||
3. The **Document QA** flow is created.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/document-qa.png",
|
||||
dark: "img/document-qa.png",
|
||||
}}
|
||||
style={{ width: "80%", margin: "20px auto" }}
|
||||
/>
|
||||
|
||||
This flow creates a basic chatbot with the **Chat Input**, **Prompt**, **OpenAI**, and **Chat Output** components.
|
||||
This chatbot is augmented with the **Files** component, which loads a file from your local machine into the **Prompt** component as `{Document}`.
|
||||
The **Prompt** component is instructed to answer questions based on the contents of `{Document}`.
|
||||
Including a file with the prompt gives the **OpenAI** component context it may not otherwise have access to.
|
||||
|
||||
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
1. In the **Variable Name** field, enter `openai_api_key`.
|
||||
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
|
||||
3. Click **Save Variable**.
|
||||
|
||||
5. To select a document to load, in the **Files** component, click within the **Path** field.
|
||||
1. Select a local file, and then click **Open**.
|
||||
2. The file name appears in the field.
|
||||
<Admonition type="tip">
|
||||
The file must be of an extension type listed [here](https://github.com/langflow-ai/langflow/blob/dev/src/backend/base/langflow/base/data/utils.py#L13).
|
||||
</Admonition>
|
||||
|
||||
## Run the Document QA flow
|
||||
|
||||
1. Click the **Run** button.
|
||||
The **Interaction Panel** opens, where you can converse with your bot.
|
||||
2. Type a message and press Enter.
|
||||
For this example, we loaded an error log `.txt` file and asked, "What went wrong?"
|
||||
The bot responded:
|
||||
```
|
||||
The issue occurred during the execution of migrations in the application. Specifically, an error was raised by the Alembic library, indicating that new upgrade operations were detected that had not been accounted for in the existing migration scripts. The operation in question involved modifying the nullable property of a column (apikey, created_at) in the database, with details about the existing type (DATETIME()), existing server default, and other properties.
|
||||
```
|
||||
|
||||
This result indicates that the bot received the loaded document and understood the context surrounding the vague question. It also correctly identified the issue in the error log, and followed up with appropriate troubleshooting suggestions. Nice!
|
||||
99
docs/docs/starter-projects/memory-chatbot.mdx
Normal file
99
docs/docs/starter-projects/memory-chatbot.mdx
Normal file
|
|
@ -0,0 +1,99 @@
|
|||
import ThemedImage from "@theme/ThemedImage";
|
||||
import useBaseUrl from "@docusaurus/useBaseUrl";
|
||||
import ZoomableImage from "/src/theme/ZoomableImage.js";
|
||||
import ReactPlayer from "react-player";
|
||||
|
||||
# Memory chatbot
|
||||
|
||||
This flow extends the [basic prompting flow](./basic-prompting.mdx) to include chat memory for unique SessionIDs.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Install Langflow.
|
||||
```bash
|
||||
python -m pip install langflow --pre
|
||||
```
|
||||
|
||||
2. Start a local Langflow instance with the Langflow CLI:
|
||||
```bash
|
||||
langflow run
|
||||
```
|
||||
Or start Langflow with Python:
|
||||
```bash
|
||||
python -m langflow run
|
||||
```
|
||||
|
||||
Result:
|
||||
```
|
||||
│ Welcome to ⛓ Langflow │
|
||||
│ │
|
||||
│ Access http://127.0.0.1:7860 │
|
||||
│ Collaborate, and contribute at our GitHub Repo 🚀 │
|
||||
```
|
||||
|
||||
Alternatively, go to [HuggingFace Spaces](https://docs.langflow.org/getting-started/hugging-face-spaces) or [Lightning.ai Studio](https://lightning.ai/ogabrielluiz-8j6t8/studios/langflow) for a pre-built Langflow test environment.
|
||||
|
||||
3. Create an [OpenAI API key](https://platform.openai.com).
|
||||
|
||||
## Create the memory chatbot project
|
||||
|
||||
1. From the Langflow dashboard, click **New Project**.
|
||||
2. Select **Memory Chatbot**.
|
||||
3. The **Memory Chatbot** flow is created.
|
||||
|
||||
<ZoomableImage
|
||||
alt="Docusaurus themed image"
|
||||
sources={{
|
||||
light: "img/memory-chatbot.png",
|
||||
dark: "img/memory-chatbot.png",
|
||||
}}
|
||||
style={{
|
||||
width: "80%",
|
||||
margin: "20px auto",
|
||||
display: "flex",
|
||||
justifyContent: "center",
|
||||
}}
|
||||
/>
|
||||
|
||||
This flow creates a basic chatbot with the **Chat Input**, **Prompt**, and **OpenAI** components.
|
||||
This chatbot is augmented with the **Chat Memory** component, which stores messages submitted via **Chat Input** and prepends them to subsequent prompts to OpenAI via `{context}`.
|
||||
The **Chat History** component gives the **OpenAI** component a memory of previous questions.
|
||||
|
||||
4. To create an environment variable for the **OpenAI** component, in the **OpenAI API Key** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
1. In the **Variable Name** field, enter `openai_api_key`.
|
||||
2. In the **Value** field, paste your OpenAI API Key (`sk-...`).
|
||||
3. Click **Save Variable**.
|
||||
|
||||
## Run the memory chatbot flow
|
||||
|
||||
1. Click the **Run** button.
|
||||
The **Interaction Panel** opens, where you can converse with your bot.
|
||||
2. Type a message and press Enter.
|
||||
The bot will respond according to the template in the **Prompt** component.
|
||||
3. Type more questions. In the **Outputs** log, your queries are logged in order. Up to 5 queries are stored by default. Try asking `What is the first subject I asked you about?` to see where the LLM's memory disappears.
|
||||
|
||||
## Modify the Session ID field to have multiple conversations
|
||||
|
||||
`SessionID` is a unique identifier in Langchain for a conversation session between a chatbot and a client.
|
||||
A `SessionID` is created when a conversation is initiated, and then associated with all subsequent messages during that session.
|
||||
|
||||
In the **Memory Chatbot** flow you created, the **Chat Memory** component references past interactions with **Chat Input** by **Session ID**.
|
||||
You can demonstrate this by modifying the **Session ID** value to switch between conversation histories.
|
||||
|
||||
1. In the **Session ID** field of the **Chat Memory** and **Chat Input** components, change the **Session ID** value from `MySessionID` to `AnotherSessionID`.
|
||||
2. Click the **Run** button to run your flow.
|
||||
In the **Interaction Panel**, you will have a new conversation. (You may need to clear the cache with the **Eraser** button).
|
||||
3. Type a few questions to your bot.
|
||||
4. In the **Session ID** field of the **Chat Memory** and **Chat Input** components, change the **Session ID** value back to `MySessionID`.
|
||||
5. Run your flow.
|
||||
The **Outputs** log of the **Interaction Panel** displays the history from your initial chat with `MySessionID`.
|
||||
|
||||
## Store Session ID as a Langflow variable
|
||||
|
||||
To store **Session ID** as a Langflow variable, in the **Session ID** field, click the **Globe** button, and then click **Add New Variable**.
|
||||
|
||||
1. In the **Variable Name** field, enter a name like `customer_chat_emea`.
|
||||
2. In the **Value** field, enter a value like `1B5EBD79-6E9C-4533-B2C8-7E4FF29E983B`.
|
||||
3. Click **Save Variable**.
|
||||
4. Apply this variable to **Chat Input**.
|
||||
|
||||
|
|
@ -61,11 +61,11 @@ We wanted to create start projects that would help you learn about new features
|
|||
|
||||
For now, we have:
|
||||
|
||||
- **[Basic Prompting (Hello, World)](/guides/basic-prompting)**: A simple flow that shows you how to use the Prompt Component and how to talk like a pirate.
|
||||
- **[Vector Store RAG](/guides/rag-with-astradb)**: A flow that shows you how to ingest data into a Vector Store and then use it to run a RAG application.
|
||||
- **[Memory Chatbot](/guides/memory-chatbot)**: This one shows you how to create a simple chatbot that can remember things about the user.
|
||||
- **[Document QA](/guides/document-qa)**: This flow shows you how to build a simple flow that helps you get answers about a document.
|
||||
- **[Blog Writer](/guides/blog-writer)**: Shows you how you can expand on the Prompt variables and be creative about what inputs you add to it.
|
||||
- **[Basic Prompting (Hello, World)](/starter-projects/basic-prompting)**: A simple flow that shows you how to use the Prompt Component and how to talk like a pirate.
|
||||
- **[Vector Store RAG](/tutorials/rag-with-astradb)**: A flow that shows you how to ingest data into a Vector Store and then use it to run a RAG application.
|
||||
- **[Memory Chatbot](/starter-projects/memory-chatbot)**: This one shows you how to create a simple chatbot that can remember things about the user.
|
||||
- **[Document QA](/starter-projects/document-qa)**: This flow shows you how to build a simple flow that helps you get answers about a document.
|
||||
- **[Blog Writer](/starter-projects/blog-writer)**: Shows you how you can expand on the Prompt variables and be creative about what inputs you add to it.
|
||||
|
||||
As always, your feedback is invaluable, so please let us know what you think of the new starter projects and what you would like to see in the future.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue