gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: add anthropic provider and new onboarding (#381)

Browse source 
* add-to-onboarding-partial

* anthropic-no-embeddings

* new-onboarding-card

* Apply suggestions from code review

Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>

* remove-preload-files-step

---------

Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com>
This commit is contained in:
Mendon Kissling 2025-11-12 12:03:10 -05:00 • committed by GitHub
parent 1385fd5d5c
commit 845bfbf384
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 30 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
docs/docs/_partial-onboarding.mdx
View file

@ -12,19 +12,18 @@ Most values from onboarding can be changed later in the OpenRAG **Settings** pag
The **language model provider** and **embeddings model provider** can only be selected at onboarding. The **language model provider** and **embeddings model provider** can only be selected at onboarding.
To change your provider selection later, you must [reinstall OpenRAG](/install#reinstall). To change your provider selection later, you must [reinstall OpenRAG](/install#reinstall).
You must use the same provider for your language model and embedding model, unless you're using Ollama. You can use different providers for your language model and embedding model, such as Anthropic for the language model and OpenAI for the embeddings model.
::: :::
Choose one LLM provider and complete only those steps: Choose one LLM provider and complete these steps:
<Tabs groupId="Provider"> <Tabs groupId="Provider">
<TabItem value="OpenAI" label="OpenAI" default> <TabItem value="OpenAI" label="OpenAI" default>
1. Enable **Get API key from environment variable** to automatically enter your key from the TUI-generated `.env` file. 1. Enable **Get API key from environment variable** to automatically enter your key from the TUI-generated `.env` file.
Alternatively, paste an OpenAI API key into the field. Alternatively, paste an OpenAI API key into the field.
2. Under **Advanced settings**, select your **Embedding Model** and **Language Model**. 2. Under **Advanced settings**, select your **Language Model**.
3. To load 2 sample PDFs, enable **Sample dataset**. 3. Click **Complete**.
This is recommended, but not required. 4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
4. Click **Complete**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**. 5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**. Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart). 6. Continue with the [Quickstart](/quickstart).
@ -33,10 +32,23 @@ Choose one LLM provider and complete only those steps:
<TabItem value="IBM watsonx.ai" label="IBM watsonx.ai"> <TabItem value="IBM watsonx.ai" label="IBM watsonx.ai">
1. Complete the fields for **watsonx.ai API Endpoint**, **IBM Project ID**, and **IBM API key**. 1. Complete the fields for **watsonx.ai API Endpoint**, **IBM Project ID**, and **IBM API key**.
These values are found in your IBM watsonx deployment. These values are found in your IBM watsonx deployment.
2. Under **Advanced settings**, select your **Embedding Model** and **Language Model**. 2. Under **Advanced settings**, select your **Language Model**.
3. To load 2 sample PDFs, enable **Sample dataset**. 3. Click **Complete**.
This is recommended, but not required. 4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
4. Click **Complete**. 5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart).
</TabItem>
<TabItem value="Anthropic" label="Anthropic">
:::info
Anthropic does not provide embedding models. If you select Anthropic for your language model, you must then select a different provider for embeddings.
:::
1. Enable **Use environment Anthropic API key** to automatically use your key from the TUI-generated `.env` file.
Alternatively, paste an Anthropic API key into the field.
2. Under **Advanced settings**, select your **Language Model**.
3. Click **Complete**.
4. In the second onboarding panel, select a provider for embeddings and select your **Embedding Model**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**. 5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**. Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart). 6. Continue with the [Quickstart](/quickstart).
@ -49,13 +61,12 @@ Choose one LLM provider and complete only those steps:
1. Enter your Ollama server's base URL address. 1. Enter your Ollama server's base URL address.
The default Ollama server address is `http://localhost:11434`. The default Ollama server address is `http://localhost:11434`.
OpenRAG automatically transforms `localhost` to access services outside of the container, and sends a test connection to your Ollama server to confirm connectivity. OpenRAG automatically transforms `localhost` to access services outside of the container, and sends a test connection to your Ollama server to confirm connectivity.
2. Select the **Embedding Model** and **Language Model** your Ollama server is running. 2. Under **Advanced settings**, select your **Language Model** from the models available on your Ollama server.
OpenRAG retrieves the available models from your Ollama server. 3. Click **Complete**.
3. To load 2 sample PDFs, enable **Sample dataset**. 4. In the second onboarding panel, select your **Embedding Model** from the models available on your Ollama server.
This is recommended, but not required.
4. Click **Complete**.
5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**. 5. To complete the onboarding tasks, click **What is OpenRAG**, and then click **Add a Document**.
Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**. Alternatively, click <Icon name="ArrowRight" aria-hidden="true"/> **Skip overview**.
6. Continue with the [Quickstart](/quickstart). 6. Continue with the [Quickstart](/quickstart).
</TabItem> </TabItem>
</Tabs> </Tabs>