Sync API¶

Reproducibility is critical for AI. For code, it's easy to keep track of changes using Github or Gitlab.For data, it's not as easy. Most of the time, we're manually writing complicated data tracking code, wrestling with an external tool, and dealing with expensive duplicate snapshot copies with low granularity.

While working with most other vector databases, if we loaded in the wrong data (or any other such mistakes), we have to blow away the index, correct the mistake, and then completely rebuild it. It'sreally difficult to rollback to an earlier state, and any such corrective actiondestroys historical data and evidence, which may be useful down the line to debug and diagnose issues.

To our knowledge, LanceDB is the first and only vector database that supports full reproducibility and rollbacks natively.Taking advantage of the Lance columnar data format, LanceDB supports:

• Automatic versioning
• Instant rollback
• Appends, updates, deletions
• Schema evolution

This makes auditing, tracking, and reproducibility a breeze!

Let's see how this all works.

Pickle Rick!¶

Let's first prepare the data. We will be using a CSV file with a bunch of quotes from Rick and Morty

Let's load this into a pandas dataframe.

It's got 3 columns, a quote id, the quote string, and the first name of the author of the quote:

We'll start with a local LanceDB connection

Creating a LanceDB table from a pandas dataframe is straightforward usingcreate_table:

Updates¶

Now, since Rick is the smartest man in the multiverse, he deserves to have his quotes attributed to his full name: Richard Daniel Sanchez.

This can be done viaLanceTable.update. It needs two arguments:

1. Awhere string filter (sql syntax) to determine the rows to update
2. A dict ofvalues where the keys are the column names to update and the values are the new values

Schema evolution¶

Ok so this is a vector database, so we need actual vectors.We'll use sentence transformers here to avoid having to deal with API keys.

Let's create a basic model using the "all-MiniLM-L6-v2" model and embed the quotes:

We can then convert the vectors into a pyarrow Table and merge it to the LanceDB Table.

For the merge to work successfully, we need to have an overlapping column. Here the natural choice is to use the id column:

And now we'll use theLanceTable.merge function to add the vector column into the LanceTable:

If we look at the schema, we see thatall-MiniLM-L6-v2 produces 384-dimensional vectors:

Rollback¶

Suppose we used the table and found that theall-MiniLM-L6-v2 model doesn't produce ideal results. Instead we want to try a larger model. How do we use the new embeddings without losing the change history?

First, major operations are automatically versioned in LanceDB.Version 1 is the table creation, with the initial insertion of data.Versions 2 and 3 represents the update (deletion + append)Version 4 is adding the new column.

We can restore version 3, before we added the old vector column

Notice that we now have one more, not less versions. When we restore an old version, we're not deleting the version history, we're just creating a new version where the schema and data is equivalent to the restored old version. In this way, we can keep track of all of the changes and always rollback to a previous state.

Switching Models¶

Now we'll switch to theall-mpnet-base-v2 model and add the vectors to the restored dataset again. Note that this step can take a couple of minutes.

Deletion¶

What if the whole show was just Rick-isms?Let's delete any quote not said by Rick:

We can see that the number of rows has been reduced to 30

Ok we had our fun, let's get back to the full quote set

History¶

We now have 9 versions in the data. We can review the operations that corresponds to each version below:

Versions:

• 1 - Create and append
• 2 - Update (deletion)
• 3 - Update (append)
• 4 - Merge (vector column)
• 5 - Restore (4)
• 6 - Merge (new vector column)
• 7 - Deletion
• 8 - Restore

Summary¶

We never had to explicitly manage the versioning. And we never had to create expensive and slow snapshots. LanceDB automatically tracks the full history of operations and supports fast rollbacks. In production this is critical for debugging issues and minimizing downtime by rolling back to a previously successful state in seconds.