Commit Graph

682 Commits

Author SHA1 Message Date
Stefano Lottini
fae14ddb89
Add Cassandra/Astra DB to the vector databases README (#665)
* Add Cassandra/Astra DB to the vector databases overall README

* Linking to a basic quickstart instead
2023-08-29 15:20:51 -07:00
Liam Thompson
31b4de22a3
Add elasticsearch examples to vector databases folder (#622)
* Add Elasticsearch to vector databases, add notebooks

* Update prompt

* Make intro verbiage more neutral

* Add semantic search notebook outputs

* Add RAG notebook output

* Update query

* Remove unreadable vector output
2023-08-29 10:54:08 -07:00
Safa Asgar
169f5e02c8
File name sanitization (#630)
* File name sanitization

URL containing reserved characters blocks file name creation.

* Regular Expression fix for Sanitized URL

Co-authored-by: Simón Fishman <simonpfish@gmail.com>

---------

Co-authored-by: Simón Fishman <simonpfish@gmail.com>
2023-08-29 10:49:23 -07:00
Stefano Lottini
4d330b82d7
Add Astra DB (/Cassandra) to vector databases with example notebooks (#655)
* first commit for the Astra DB / Cassandra notebooks

* add json with quotes

* towards the final cassIO pilot notebook

* small changes to the copy

* cassIO pilot completed and its readme done

* fix silly markdown error

* fix silly markdown error 2

* astra vector link change and vector search picture improved

* added link to docs for connecting to Cassandra cluster

* CQL version of the flow

* revised readme

* final adjustments around metrics/distances

* links' final version assumes files in openai's main branch

* Add ref to QA+vector general guide; fix prompt; clarified conclusion paragraph; typos
2023-08-29 10:27:49 -07:00
Simón Fishman
2e9704b3b3
update semantic kernel link (#662)
the previous link pointed to a blog with multiple articles. this is a clearer link to point to
2023-08-28 18:32:29 -07:00
recordcrash
1945bfe65c
Fix UTF-8 encoding in Chat_finetuning_data_prep.ipynb (#648) 2023-08-28 18:12:30 -07:00
Eliah Kagan
63f95154b1
Add Tiktokenizer link in "How to count tokens" (#604)
This adds a link to Tiktokenizer webapp as another tool, in
addition to the OpenAI Tokenizer.
2023-08-28 10:28:19 -07:00
Christine Belzie
45c6406e8b
[revise] small edits and fixed typos (#510)
* [revise] made small edits and fixed typos

* fix: revert back to original descriptions

* small language updates

---------

Co-authored-by: Simón Fishman <simonpfish@gmail.com>
2023-08-25 13:08:49 -07:00
Viet Hoang Tran Duong
1ae3bf631b
fix undefined variables in fine tune example (#660)
`create_user_message` and `test_df` are not defined.
2023-08-25 13:03:06 -07:00
Simón Fishman
35b7123faf
update titles (#653) 2023-08-22 16:32:43 -07:00
Simón Fishman
d534c85477
more fine-tuning improvements (#652)
* more fine-tuning improvements

* add links to other resources
2023-08-22 16:27:08 -07:00
Simón Fishman
8ed84645e8
small improvements to the fine-tuning cookbook (#651) 2023-08-22 15:30:03 -07:00
Logan Kilpatrick
64e9471909
update readme to link fine-tuning guide (#650) 2023-08-22 14:09:03 -07:00
simonpfish
cbe292bd93 update fine-tuning cookbook 2023-08-22 13:48:39 -07:00
Michael Wu
a173325830
add ft data prep notebook (#647) 2023-08-22 12:24:42 -07:00
colin-openai
524949f9d1
Pushing cookbook for fine-tuning via ChatCompletion (#646)
* Pushing cookbook for fine-tuning via ChatCompletion

* Add correct file

* Fixed bug with create_prompt function and refactored files
2023-08-22 12:24:22 -07:00
aalmaksour82
a74a7a7940
Fixed JSON formatting bug in arxiv_functions (#562) 2023-08-18 09:26:04 +01:00
Ikko Eltociear Ashimine
6597537307
Fix typo in redis-hybrid-query-examples.ipynb (#642)
bellow -> below
2023-08-17 03:21:48 -07:00
Shyamal H Anadkat
57ec84f016
Update recently added (#641)
* Update recently added

* Update README.md

Co-authored-by: Simón Fishman <simonpfish@gmail.com>

---------

Co-authored-by: Simón Fishman <simonpfish@gmail.com>
2023-08-16 17:59:19 -07:00
Simón Fishman
b3a41db9da
fix date typo (#640) 2023-08-16 17:38:48 -07:00
Shyamal H Anadkat
9f63c4863e
Adds reference to SummEval (#639) 2023-08-16 14:20:22 -07:00
Simón Fishman
1d73635488
various minor improvements (#638) 2023-08-16 10:53:54 -07:00
Shyamal H Anadkat
346617e8fd
adds notebook on abstractive summarization eval (#637) 2023-08-16 10:25:42 -07:00
prestontuggle
4912564dc1
adds one function calling notebook (#629)
* adds one function calling notebook

* reordered imports and ran all cells

* fixed comma error
2023-08-11 20:34:29 -04:00
prestontuggle
0933dd1569
adds two Whisper guides (#628)
* adds two Whisper guides

* polishing

* fixes function argument misordering

---------

Co-authored-by: Ted Sanders <ted@openai.com>
2023-08-11 16:11:19 -04:00
Shantanu Nair
8e6e058c6a
Fix function description (#626) 2023-08-09 10:34:59 -07:00
Ted Sanders
c651bfdda6
Add prompttools to prompting libraries (#620) 2023-08-01 22:51:45 -07:00
Anton Troynikov
3115683f14
Update notebooks (#598) 2023-07-24 15:59:33 -07:00
richzw
964dd85ed3
add tiktoken-go to How_to_count_tokens_with_tiktoken.ipynb (#605) 2023-07-24 15:54:52 -07:00
Krista Pratico
5e050080ab
[azure] add functions notebook sample (#595)
* add azure functions notebook sample

* update api key to use env var + note use of env vars over config in code across azure samples
2023-07-21 16:38:49 -07:00
ancri
b5ea5f3b0e
consolidate Embedding.create calls into one (#543) 2023-07-20 20:20:04 -07:00
Tomas Dulka
4fd2b1a6d2
replace eval with safer literal_eval (#561) 2023-07-17 16:40:54 -07:00
Sebastian Witalec
3bd18cc07d
fix markdown typo on a link (#591) 2023-07-17 15:53:44 -07:00
Alex Dhillon
9dad13d05b
simplify pretty print (#575) 2023-07-16 14:22:46 -07:00
Yoav Farhi
5c1d46ade7
Update the actual number of results used in generating the final answer (#587)
The comment mentions 20, but it actually uses 5
2023-07-13 10:47:49 -07:00
Moiz Sajid
e4c4d3baa9
Updated README.md in examples/vector_databases (#581)
Added the links to the missing vector databases
2023-07-12 12:28:45 -07:00
Ikko Eltociear Ashimine
e983502569
Fix typo in QA_with_Langchain_AnalyticDB_and_OpenAI.ipynb (#582)
futher -> further
2023-07-12 12:28:14 -07:00
Jason M
cd62830788
Update How_to_call_functions_with_chat_models.ipynb (#545)
Updates "min" parameter to "multiplier". Should run the same.
2023-07-11 17:38:33 -07:00
liuchengshan-lcs
238ff54fce
Add getting started with PolarDB vector database and OpenAI example. (#489) 2023-07-11 17:13:26 -07:00
Douglas Blank
6d0ffe31a9
Added notebook example for visualizing embeddings in Kangas (#469)
* Added notebook example for visualizing embeddings in Kangas

Plots UMAP projection space, one per row, in open source Kangas DataGrid.

For more information about Kangas, see: https://github.com/comet-ml/kangas

* Moved notebook to third_party_examples
2023-07-11 17:11:16 -07:00
Eli
bd91363afa
Enhancements and Refactoring of Python Code Extraction Methods (#467)
* Refactor and enhance code extraction methods.

* Use f-strings to print filepaths, improving readability.
2023-07-11 17:08:37 -07:00
Ted Sanders
17858f204f
fixes token counting in translate_latex_book.ipynb (#579)
* fixes token counting in translate_latex_book.ipynb

* adds back comment
2023-07-11 17:00:38 -07:00
Ted Sanders
07c0351216
Update README.md with fixed vector DB link (#576) 2023-07-10 12:31:35 -07:00
sun zhun
950246dd08
Update How_to_handle_rate_limits.ipynb (#554)
Replace deprecated model "code-cushman-001" with "gpt-3.5-turbo".
2023-06-29 22:23:39 -07:00
Kacper Łukawski
3ce532c03c
Refactor Qdrant notebooks (#556)
* Upgrade Qdrant to 1.3.0

* Adapt the descriptions and run the missing cells
2023-06-29 07:47:18 -07:00
shayarnett
090b1f95ce
Update broken link in README.md (#558)
Reranking search with cross-encoders link was incorrect.
2023-06-29 07:46:24 -07:00
colin-openai
bad59002d1
Splitting Vector Databases into individual cookbooks (#529)
* Initial commit of vector database cookbooks split out individually

* Moved notebooks to each provider's named folder and updated the README

* Removed vector DB overall cookbook in favour of individual directories
2023-06-28 01:37:01 -07:00
colin-openai
f53a22e29f
Initial commit of reranking with cross-encoder cookbook (#483)
* Initial commit of reranking with cross-encoder cookbook

* Added logit bias for Yes and No in this case

* Reran end-to-end

* Updated based on Ted's comments

* Rerun with Ted's comments
2023-06-28 00:59:23 -07:00
Filip Haltmayer
f4c67dff3c
update to token for zilliz (#552)
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
2023-06-27 12:53:26 -07:00
prestontuggle
3170356cc2
Adds Whisper Prompting Guide (#551) 2023-06-27 14:24:26 -04:00