docetl/docs/operators
Shreya Shankar bcac6872f5
Embedding blocking threshold optimization (#473)
* feat: Add runtime blocking threshold optimization

Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>

* Checkpoint before follow-up message

Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>

* Refactor: Simplify target_recall retrieval in Equijoin and Resolve

Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>

* Refactor: Improve blocking documentation and add auto-blocking

Co-authored-by: ss.shankar505 <ss.shankar505@gmail.com>

* allow resolve and equijoin to figure out blocking thresholds on the fly.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-29 19:47:21 -06:00
..
cluster.md Update cluster documentation to use inputs iteration in summary prompt (#386) 2025-07-14 18:12:22 -07:00
code.md add limit param to llm ops (#466) 2025-12-26 19:46:28 -08:00
equijoin.md Embedding blocking threshold optimization (#473) 2025-12-29 19:47:21 -06:00
extract.md add limit param to llm ops (#466) 2025-12-26 19:46:28 -08:00
filter.md add limit param to llm ops (#466) 2025-12-26 19:46:28 -08:00
gather.md Refactor: Use num_tokens instead of token_count (#430) 2025-09-15 15:32:33 -07:00
link-resolve.md Added docs 2024-10-22 14:54:27 +02:00
map.md add limit param to llm ops (#466) 2025-12-26 19:46:28 -08:00
parallel-map.md fix: improve caching and don't raise error for bad gather configs (#373) 2025-06-30 23:19:17 -07:00
rank.md feat: add extract operator (#361) 2025-05-13 17:43:46 -07:00
reduce.md add limit param to llm ops (#466) 2025-12-26 19:46:28 -08:00
resolve.md Embedding blocking threshold optimization (#473) 2025-12-29 19:47:21 -06:00
sample.md feat: add topk implementation (#410) 2025-08-13 13:27:54 -07:00
split.md docs: add sample parameter (#87) 2024-10-08 22:36:46 -07:00
topk.md feat: add topk implementation (#410) 2025-08-13 13:27:54 -07:00
unnest.md docs: add sample parameter (#87) 2024-10-08 22:36:46 -07:00