Commit graph

47 commits

Author SHA1 Message Date
Simon Willison
0865c2d939 LLM_RAISE_ERRORS debug feature, closes #817 2025-03-04 20:14:32 -08:00
Tomoko Uchida
eda1f4f588
Add note about similarity function in "similar" command's doc (#774)
* note about similarity function in similar command doc
* Link to Wikipedia definition

---------

Co-authored-by: Simon Willison <swillison@gmail.com>
2025-02-26 10:07:10 -08:00
Simon Willison
747d92ea4f Docs for multiple -q option, closes #748 2025-02-13 16:01:02 -08:00
Simon Willison
9a1374b447
llm embed-multi --prepend option (#746)
* llm embed-multi --prepend option

Closes #745
2025-02-12 15:19:18 -08:00
Simon Willison
562fefb374 Use 3-small in docs instead of ada-002
Spotted while working on #537
2024-07-18 12:23:49 -07:00
Simon Willison
044689351d Support new OpenAI embeddings models, refs #394 2024-01-25 13:10:41 -08:00
Simon Willison
8e84c00771
Link to blog post about building Jina embeddings plugin 2023-10-27 07:40:33 -07:00
Simon Willison
356fcb72f6 NumPy decoding docs, plus extra tests for llm.encode/decode
!stable-docs

Refs https://discord.com/channels/823971286308356157/1128504153841336370/1151975583237034056
2023-09-14 14:01:47 -07:00
Simon Willison
33dee4762e llm embed-multi --batch-size option, closes #273 2023-09-13 16:33:27 -07:00
Simon Willison
b9478e6a17 batch_size= argument to embed_multi(), refs #273 2023-09-13 16:24:04 -07:00
Simon Willison
e6dac1a1bd Documentation for building binary embedding plugins, refs #264 2023-09-12 11:32:12 -07:00
Simon Willison
4952a8d119 llm similar --binary, closes #269 2023-09-12 11:23:31 -07:00
Simon Willison
506de80f69 Renamed binary.md to storage.md and documented --binary embeddings, refs #264 2023-09-12 11:15:17 -07:00
Simon Willison
eea7b4e0fb Various documentation copy improvements, refs #264 2023-09-12 11:04:45 -07:00
Simon Willison
90ab024604 Release 0.10a1
Refs #229, #244, #247, #248, #254, #256, #259, #263
2023-09-11 22:57:54 -07:00
Simon Willison
52cec1304b
Binary embeddings (#254)
* Binary embeddings support, refs #253
* Write binary content to content_blob, with tests - refs #253
* supports_text and supports_binary embedding validation, refs #253
2023-09-11 18:58:44 -07:00
Simon Willison
5ba34dbe36 llm embed-db is now llm collections, refs #229 2023-09-10 14:24:27 -07:00
Simon Willison
4f1b59b67b Tiny change to force a docs update
!stable-docs

Refs #249
2023-09-08 17:59:27 -07:00
Simon Willison
d0f435af53 Fixed bug in llm embed-multi documentation, closes #249 2023-09-08 17:58:41 -07:00
Simon Willison
a74f63f421
Link to blog post
!stable-docs
2023-09-04 15:28:48 -07:00
Simon Willison
78a0e9bd44 llm --files --encoding option and latin-1 fallback, closes #225 2023-09-04 12:28:31 -07:00
Simon Willison
62dd006099
Bold collection
!stable-docs
2023-09-04 08:30:45 -07:00
Simon Willison
a44e23876e
Fix broken example in docs (#223) 2023-09-03 20:53:51 -07:00
Simon Willison
5efb300c42 Release 0.9
Refs #192, #209, #211, #213, #215, #217, #218, #219, #222

Closes #205
2023-09-03 19:35:14 -07:00
Simon Willison
f842fbea49 Mention brute-force approach, link to vector indexing issue
Refs #216. Closes #214
2023-09-03 19:10:42 -07:00
Simon Willison
3bf781fba2 Duplicate content is only embedded once, closes #217 2023-09-03 17:39:11 -07:00
Simon Willison
0eda99e91c Default embedding model finishing touches, closes #222 2023-09-03 17:21:47 -07:00
Simon Willison
8ce7046d13 Documentation for llm embed-multi, refs #215 2023-09-03 16:40:00 -07:00
Simon Willison
0da1ed7d98 --remove-default for llm embed-models default, refs #222 2023-09-03 16:40:00 -07:00
Simon Willison
213e0b0c75 embed-db delete-collection command and .delete() method, closes #219 2023-09-03 12:55:48 -07:00
Simon Willison
a5d6b580ba Store content_hash in embeddings table, refs #217
Uses new migrations feature from https://github.com/simonw/sqlite-migrate/issues/9
2023-09-03 10:50:51 -07:00
Simon Willison
26332045dd llm embed --metadata option, closes #209 2023-09-03 07:43:23 -07:00
Simon Willison
b7e6c1675b Show SQL schema for embeddings in docs 2023-09-02 20:48:00 -07:00
Simon Willison
51488c579b Collection now defaults to in-memory DB, closes #213 2023-09-02 15:43:20 -07:00
Simon Willison
e49c816e18 Drop llm.EmbeddingModel.embedding_size property, closes #208 2023-09-02 08:45:17 -07:00
Simon Willison
3d56d6cc24 Collection design tweaks + llm embed/similar now use it, closes #204 2023-09-02 08:30:56 -07:00
Simon Willison
3b2d5bf7f9 embed_multi and embed_multi_with_metadata, closes #202 2023-09-01 20:15:28 -07:00
Simon Willison
4be89facb5 Fixed and finished llm similar command, closes #190 2023-09-01 19:01:16 -07:00
Simon Willison
de6d257dde collection.similar now returns List[Entry], closes #203 2023-09-01 18:06:56 -07:00
Simon Willison
d2f3d319c2 Test and docs for collection.embed(metadata=), refs #203 2023-09-01 17:57:54 -07:00
Simon Willison
4955a5fa6c Docs and test for store=True, refs #203 2023-09-01 17:52:43 -07:00
Simon Willison
212cd617f3 Initial Python embeddings API docs, refs #191 2023-09-01 17:25:45 -07:00
Simon Willison
7a4429f100 Fix mypy errors
Refs https://github.com/simonw/llm/issues/191#issuecomment-1703266224
2023-09-01 13:14:59 -07:00
Simon Willison
817aff8bae Embeddings now happen in batches, closes #200 2023-08-31 22:27:06 -07:00
Simon Willison
02f671219e Improvements to embedding docs, refs #185 2023-08-31 21:55:39 -07:00
Simon Willison
5a9269a2ce
Typo 2023-08-31 16:58:02 -07:00
Simon Willison
77cf56e54a
Initial CLI support and plugin hook for embeddings, refs #185
* Embeddings plugin hook + OpenAI implementation
* llm.get_embedding_model(name) function
* llm embed command, for returning embeddings or saving them to SQLite
* Tests using an EmbedDemo embedding model
* llm embed-models list and emeb-models default commands
* llm embed-db path and llm embed-db collections commands
2023-08-27 22:24:10 -07:00