One post tagged with "chunking"

Announcing the release of Spice v0.18.3-beta 🛠️

The Spice v0.18.3-beta release includes several quality-of-life improvements including verbosity flags for spiced and the Spice CLI, vector search over larger documents with support for chunking dataset embeddings, and multiple performance enhancements. Additionally, the release includes several bug fixes, dependency updates, and optimizations, including updated table providers and significantly improved GitHub data connector performance for issues and pull requests.

Highlights in v0.18.3-beta​

GitHub Query Mode: A new github_query_mode: search parameter has been added to the GitHub Data Connector, which uses the GitHub Search API to enable faster and more efficient query of issues and pull requests when using filters.

Example spicepod.yml:

- from: github:github.com/spiceai/spiceai/issues/trunk
  name: spiceai.issues
  params:
    github_query_mode: search # Use GitHub Search API
    github_token: ${secrets:GITHUB_TOKEN}

Output Verbosity: Higher verbosity output levels can be specified through flags for both spiced and the Spice CLI.

Example command line:

spice -v
spice --very-verbose

spiced -vv
spiced --verbose

Embedding Chunking: Chunking can be enabled and configured to preprocess input data before generating dataset embeddings. This improves the relevance and precision for larger pieces of content.

Example spicepod.yml:

- name: support_tickets
  embeddings:
    - column: conversation_history
      use: openai_embeddings
      chunking:
        enabled: true
        target_chunk_size: 128
        overlap_size: 16
        trim_whitespace: true

For details, see the Search Documentation.