mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-28 10:26:27 +00:00
b752da1cd5
* new docs version * updated directory structure * Add pipelines page * Add Finder deprecation suggestion * header for pipelines file * Document MySQL support * Mention DPR train tutorial coming soon * Mention open distro ES * Update doc strings regarding similarity fn * Add link to API docs * Wrap pipelines docs in box * add api reference for pipelines * copied latest version to v0.6.0 * Remove space * Remove space * Copy to v0.6.0 Co-authored-by: brandenchan <brandenchan@icloud.com>
1.1 KiB
1.1 KiB
Generator
Example
See Tutorial 7 for a guide on how to build your own generative QA system.
While extractive QA highlights the span of text that answers a query, generative QA can return a novel text answer that it has composed. The best current approaches, such as Retriever-Augmented Generation, can draw upon both the knowledge it gained during language model pretraining (parametric memory) as well as passages provided to it with a retriever (non-parametric memory). With the advent of Transformer based retrieval methods such as Dense Passage Retrieval, retriever and generator can be trained concurrently from the one loss signal.
Pros
- More appropriately phrased answers
- Able to syntehsize information from different texts
- Can draw on latent knowledge stored in language model
Cons
- Not easy to track what piece of information the generator is basing its response off of