feat: Update website documentation to support the ability for ollama …

…to do embedding (#15)
bosun-ai · Sep 8, 2024 · 6e1f658 · 6e1f658
1 parent 4d00887
commit 6e1f658
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/src/content/docs/concepts/prompting-embedding.md b/src/content/docs/concepts/prompting-embedding.md
@@ -40,8 +40,8 @@ Or in human language: "Given a list of things to Embed, give me embeddings". The
 | OpenAI                     | Implements both SimplePrompt and Embed via `async_openai`                   | openai       |
 | FastEmbed                  | Implements Embed via `fastembed-rs`, including many dense and sparse models | fastembed    |
 | Titan (Bedrock)            | AWS Titan via Bedrock                                                       | aws-bedrock  |
-| Anthropic models (Bedrock) | Recen Anthropic models via Bedrock                                          | aws-bedrock  |
+| Anthropic models (Bedrock) | Recent Anthropic models via Bedrock                                         | aws-bedrock  |
 | Groq                       | Implements `SimplePrompt`                                                   | groq         |
-| ollama                     | Local models via ollama.rs implementing SimplePrompt                        | ollama       |
+| ollama                     | Implements both SimplePrompt and Embed via `ollama-rs`, using local models  | ollama       |
 
 </small>
diff --git a/src/content/docs/concepts/transforming-and-enriching.mdx b/src/content/docs/concepts/transforming-and-enriching.mdx
@@ -76,7 +76,7 @@ pipeline.then_in_batch(10, |mut nodes| {
 
 | Name                      | Description                                                    | Feature Flag |
 | ------------------------- | -------------------------------------------------------------- | ------------ |
-| Embed                     | Generic embedding transformer, requires an LLM                 |              |
+| Embed                     | Generic embedding transformer, requires an embedding model     |              |
 | MetadataKeywords          | Uses an LLM to extract keywords and add as metadata            |              |
 | MetadataQACode            | Uses an LLM to generate questions and answers for Code         |              |
 | MetadataQAText            | Uses an LLM to generate questions and answers for Text         |              |

diff --git a/src/content/docs/getting-started/features.mdx b/src/content/docs/getting-started/features.mdx
@@ -38,7 +38,7 @@ For all our integrations and tools we aim to provide sane defaults to get you st
 | AWS Bedrock | <Icon name="approve-check-circle" /> |                                      | aws-bedrock  | Mistral and Titan models supported                                                     |
 | groq        | <Icon name="approve-check-circle" /> |                                      | groq         | All major models supported, uses async_openai with Groq's openai schema under the hood |
 | FastEmbed   |                                      | <Icon name="approve-check-circle" /> | fastembed    | Uses fastembed.rs under the hood, dense and sparse embedding models supported          |
-| Ollama      | <Icon name="approve-check-circle" /> |                                      | ollama       | Ollama support                                                                         |
+| Ollama      | <Icon name="approve-check-circle" /> | <Icon name="approve-check-circle" /> | ollama       | Ollama support                                                                         |
 
 ## Additional integrations