mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-24 02:05:11 +08:00
71fbf5ff00
* version-1.9.0-docs * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
58 lines
3.3 KiB
Plaintext
58 lines
3.3 KiB
Plaintext
---
|
|
title: CometAPI
|
|
slug: /bundles-cometapi
|
|
description: Use CometAPI models in Langflow to generate text or output a Language Model for downstream Components.
|
|
---
|
|
|
|
import Icon from "@site/src/components/icon";
|
|
|
|
[Bundles](/components-bundle-components) contain custom components that support specific third-party integrations with Langflow.
|
|
|
|
This page describes the components that are available in the **CometAPI** bundle.
|
|
|
|
For more information about CometAPI features and functionality used by CometAPI components, see the [CometAPI documentation](https://www.cometapi.com/).
|
|
|
|
## CometAPI text generation
|
|
|
|
This component generates text using CometAPI's language models through the CometAPI OpenAI-compatible endpoints.
|
|
|
|
It can output either a **Model Response** ([`Message`](/data-types#message)) or a **Language Model** ([`LanguageModel`](/data-types#languagemodel)).
|
|
|
|
Use the **Language Model** output when you want to use a CometAPI model as the LLM for another LLM-driven component, such as an **Agent** or **Smart Transform** component.
|
|
|
|
For more information, see [Language model components](/components-models).
|
|
|
|
### CometAPI parameters
|
|
|
|
import PartialParams from '@site/docs/_partial-hidden-params.mdx';
|
|
|
|
<PartialParams />
|
|
|
|
| Name | Type | Description |
|
|
|------|------|-------------|
|
|
| api_key | SecretString | Input parameter. Your CometAPI API Key for authentication. |
|
|
| model_name | String | Input parameter. The id of the CometAPI model to use. The component automatically fetches the latest available models from CometAPI when you provide a valid API key. For information about supported models, see the [CometAPI documentation](https://www.cometapi.com/). |
|
|
| input_value | String | Input parameter. The input text to send to the model. |
|
|
| system_message | String | Input parameter. A system message that helps set the behavior of the assistant. |
|
|
| max_tokens | Integer | Input parameter. The maximum number of tokens to generate. Set to 0 for unlimited tokens. |
|
|
| temperature | Float | Input parameter. Controls randomness in the output. Range: `[0.0, 2.0]`. Default: `0.7`. |
|
|
| seed | Integer | Input parameter. The seed controls the reproducibility of the job. |
|
|
| model_kwargs | Dict | Input parameter. Additional keyword arguments to pass to the model. |
|
|
| json_mode | Boolean | Input parameter. If True, it will output JSON regardless of passing a schema. |
|
|
| stream | Boolean | Input parameter. Whether to stream the response. Default: false. |
|
|
| model | LanguageModel | Output parameter. An instance of ChatOpenAI configured with CometAPI parameters. |
|
|
|
|
## Use CometAPI in a flow
|
|
|
|
1. Sign up for a [CometAPI account](https://www.cometapi.com/).
|
|
2. Obtain your API key from the CometAPI dashboard.
|
|
3. In Langflow, add the **CometAPI** component to your flow.
|
|
4. Enter your API key in the **CometAPI API Key** field.
|
|
5. Select your preferred model from the **Model Name** menu.
|
|
6. Configure other parameters as needed for your use case.
|
|
7. Add other components to your flow as needed.
|
|
|
|
To perform a basic test, add **Chat Input** and **Chat Output** components to your flow, connect them to the **CometAPI** component accordingly, and then click **Playground** to test the connection and chat with your model.
|
|
|
|
For more advanced use cases, you can connect the CometAPI component to other components like **Prompt Template**, **Agent**, or **Smart Transform** components.
|