Add dimension support for OpenAI embeddings

[izellevy]

Problem

New OpenAI embedding models support controlling the dimension parameter for the embeddings vectors. We cannot currently pass a dynamic dimension to OpenAI models.

Solution

Updated the pinecone-text package version that supports passing dimension to the Encoder. Changed the default embedding model to the new one (text-embedding-3-small). Removed support for taking the dimension on create_canopy_index. From now on, we always rely on the RecordEncoder's dimension to create the index.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update
• Infrastructure change (CI configs, etc)
• Non-code change (docs, etc)
• None of the above: (explain here)

Test Plan

Describe specific steps for validating this change.

[acatav]

LGTM!