chore: Improve quickstart #374
Open
+93
−19
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
JamesGuthrie
approved these changes
Jan 18, 2025
|
|
||
| - Automatic creation and synchronization of vector embeddings for your data | ||
| - Seamless vector and semantic search | ||
| - Retrieval Augmented Generation(RAG) directly in SQL |
There was a problem hiding this comment.
Suggested change
| - Retrieval Augmented Generation(RAG) directly in SQL | |
| - Retrieval Augmented Generation (RAG) directly in SQL |
| @@ -125,7 +134,9 @@ This section will walk you through the steps to get started with pgai and Ollama | |||
|
|
|||
| 1. **Search the embeddings** | |||
|
|
|||
| We'll search the embeddings for the concept of "properties of light" | |||
| We'll search the embeddings for the concept of "properties of light" even though these words are not in the text of the articles. This is only possible because of vector embeddings that capture the semantic meaning of the text. | |||
There was a problem hiding this comment.
Suggested change
| We'll search the embeddings for the concept of "properties of light" even though these words are not in the text of the articles. This is only possible because of vector embeddings that capture the semantic meaning of the text. | |
| We'll search the embeddings for the concept of "properties of light" even though these words are not in the text of the articles. This is possible because vector embeddings capture the semantic meaning of the text. |
| ``` | ||
| And now you don't need to do anything to update the embeddings. The vectorizer will automatically create the embeddings for the new row with any intervention from you. After a few seconds, you can run the search query again to see the new embedding. | ||
| And now you don't need to do anything to update the embeddings. The vectorizer will automatically create the embeddings for the new row with any intervention from you. After a few seconds, you can run the following search query to see the new embedding: |
There was a problem hiding this comment.
Suggested change
| And now you don't need to do anything to update the embeddings. The vectorizer will automatically create the embeddings for the new row with any intervention from you. After a few seconds, you can run the following search query to see the new embedding: | |
| And now you don't need to do anything to update the embeddings. The vectorizer will automatically create the embeddings for the new row without any intervention from you. After a few seconds, you can run the following search query to see the new embedding: |
There was a problem hiding this comment.
Looks good!
- I think we need to add somewhere early, what the auto-generated (in this case
wiki_embeddings) view does. I don't know that it's something that's exactly analogous to other vector databases? I know other DBs store metadata along with chunks, but it might be nice to clarify early on what most of the queries are running against, e.g. most of the semantic search and RAG queries are against thewiki_embeddingsview.
| ```sql | ||
| SELECT title, chunk | ||
| FROM wiki_embeddings | ||
| ORDER BY embedding <=> ai.ollama_embed('all-minilm', 'AI tools') |
There was a problem hiding this comment.
Maybe a SQL comment here to explain how this translates to seeing the latest embedding?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.