initial-content

This commit is contained in:
Mendon Kissling 2024-04-22 21:22:43 -04:00
commit d5c43a0bf2
5 changed files with 128 additions and 87 deletions

View 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](/guides/memory-chatbot.mdx)
* [Blog writer](/guides/blog-writer.mdx)
* [Document QA](/guides/document-qa.mdx)