# IBM Watsonx

## Prerequisite

1. Register an account on [IBM Watsonx](https://www.ibm.com/watsonx)
2. Create a new project:

<figure><img src="/files/kkLvZMLio2JhDPWwnFVA" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/Zx76wrxtdUHiAWAja5Gv" alt=""><figcaption></figcaption></figure>

3. After project has been created, back to the main dashboard, and click **Explore foundation models**:

<figure><img src="/files/5Ffck4CoBYGLJMKDJGH5" alt=""><figcaption></figcaption></figure>

4. Choose the model you would like to use and open in Prompt Lab:

<figure><img src="/files/0aE17S8zaldEQsi3Ugfm" alt=""><figcaption></figcaption></figure>

5. From the top right corner, click on View Code:

<figure><img src="/files/vnD1pXNZsJ6Bv9lhykK8" alt=""><figcaption></figcaption></figure>

6. Take note on the `model_id` and `version` parameter. In this case, it is `ibm/granite-3-8b-instruct,` and the version is `2023-05-29`.
7. Click the navigation bar from the left side, and click Developer access

<figure><img src="/files/BgKGnVxmY4tpdqb00AxV" alt="" width="308"><figcaption></figcaption></figure>

8. Take note on the `watsonx.ai URL`, `Project ID` and create a new API key from IBM Cloud Console.
9. By now, you should have the following information:
   * Watsonx.ai URL
   * Project ID
   * API Key
   * Model's version
   * Model's ID

## Setup

1. **Chat Models** > drag **ChatIBMWatsonx** node

<figure><img src="/files/L5eoTp8I2Ex0CWF61zB3" alt="" width="306"><figcaption></figcaption></figure>

2. Fill in the Model with the Model ID earlier. Create New Credential and fill in all the details.

<figure><img src="/files/PnCNNhcSxHGWg3vHyNvU" alt="" width="419"><figcaption></figcaption></figure>

2. Voila [🎉](https://emojipedia.org/party-popper/), you can now use **ChatIBMWatsonx node** in Flowise!

<figure><img src="/files/h56b4lndR1W5Ukr0SZl5" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.flowiseai.com/integrations/langchain/chat-models/ibm-watsonx.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.