266 Commits

Author SHA1 Message Date
Ian Arawjo
5d4b76cf72 Fix PaLM temp=0 build, update package vers and rebuild react 2023-06-30 14:59:00 -04:00
Ian Arawjo
3de49fd743 Added Comment Nodes. Rebuilt react. 2023-06-30 12:55:20 -04:00
Ian Arawjo
17a789cb40 Remove flask app calls and socketio server that are no longer used 2023-06-30 12:09:31 -04:00
Ian Arawjo
7543ccdd8b Added back Dalai call support, routing through Flask 2023-06-30 11:41:02 -04:00
Ian Arawjo
e8ad23f7bb Added HuggingFace models API 2023-06-29 21:53:04 -04:00
Ian Arawjo
34884345d9 Refactored to LLMProvider to streamline model additions 2023-06-29 17:29:10 -04:00
Ian Arawjo
d401216744 Changed all example flows to use JS. Bug fix in query.ts 2023-06-29 15:22:52 -04:00
Ian Arawjo
603f253993 Check browser compat and display error if not supported 2023-06-29 10:58:04 -04:00
Ian Arawjo
d116ef75a8 Remove/error out on Python eval nodes when not running locally. 2023-06-29 10:22:22 -04:00
Ian Arawjo
0af418934a Edits to info modal on Eval node 2023-06-29 10:07:50 -04:00
Ian Arawjo
310375968a Added info button to Eval nodes. Rebuilt react 2023-06-29 09:57:35 -04:00
Ian Arawjo
1564c83ae9 Route Anthropic calls through Flask when running locally 2023-06-28 18:05:09 -04:00
Ian Arawjo
41e241a1d4 Added fetchEnvironAPIKeys to Flask server to fetch os.environ keys when running locally 2023-06-28 12:08:26 -04:00
Ian Arawjo
e885f33e70 Tested TypeScript backendgit status! :) woot 2023-06-28 12:07:41 -04:00
Ian Arawjo
590d86cc7b wip swapping backends 2023-06-27 17:52:53 -04:00
Ian Arawjo
5276f683bf Tested and working JS Evaluator execution. 2023-06-27 13:03:33 -04:00
Ian Arawjo
11a896d8c2 Execute JS code on iframe sandbox 2023-06-27 12:24:14 -04:00
Ian Arawjo
b3751eab97 Added craco for optional webpack config. Config'd for TypeScript with Node.js packages browserify'd 2023-06-27 11:58:56 -04:00
Ian Arawjo
022f2a89b3 Added execute() and tested w concrete func. Need to test eval() 2023-06-26 21:24:56 -04:00
Ian Arawjo
5368aee29c wip execute() in backend.ts 2023-06-26 13:44:22 -04:00
Ian Arawjo
18885b4b89 Tested queryLLM and StorageCache compressed saving/loading 2023-06-26 10:08:58 -04:00
Ian Arawjo
476e59365f wip converting queryLLM in flask_app to TS 2023-06-25 22:52:44 -04:00
Ian Arawjo
d61bd922ca jest tests for query, utils, template.ts. Confirmed PromptPipeline works. 2023-06-25 14:02:25 -04:00
Ian Arawjo
dc02e8f44a more progress on converting utils.py to Typescript 2023-06-24 21:03:26 -04:00
Ian Arawjo
a66a5c73f2 wip started utils.js conversion. Tested that OpenAI API call works 2023-06-24 16:32:36 -04:00
Ian Arawjo
dca20c2d0e wip converting query.py to query.ts 2023-06-24 13:45:50 -04:00
Ian Arawjo
188c10f71f Change all fetch() calls to fetch_from_backend switcher 2023-06-24 11:12:08 -04:00
Ian Arawjo
54f6de0184 wip 2023-06-24 08:21:43 -04:00
Ian Arawjo
87e140649c Beginning to convert Python backend to Typescript 2023-06-24 08:21:42 -04:00
Ian Arawjo
9b0d3a7779 group by different 'LLM sets' in Vis Nodes 2023-06-23 18:07:23 -04:00
Ian Arawjo
ef51e9e9cf Minor bug fix with empty response str in Vis Node v0.1.7.2 2023-06-23 09:28:40 -04:00
ianarawjo
be9c176f7c
Autosaving, on the way to better plots (#78)
* Flow autosaving every 60 seconds

* Set viewport upon resetFlow

* Added x-axis, y-axis etc header to Vis node. Ensured left padding sizes to shortnames.

* When num gen per prompt = 1, now plots single bar chart w solid LLM color

* Rebuilt react and update package version
2023-06-23 09:16:48 -04:00
ianarawjo
4bd5c15e82
Immediate bug fix when extending ChainForge examples that were created before the new OpenAI 'functions' feature (#77)
* Fix bug in call_chatgpt

* Bug fix and add New Flow button
2023-06-21 13:55:44 -04:00
ianarawjo
ea3d730bba
Merge 0.1.7 (#76)
* Added asMarkdownAST to ResponseInfo

* Increased margin between LLM responses in response inspector

* Added Inspect Results footer to eval node after run

* Fixed bug when cacheing responses after deleting a model and adding a new one

* Fixed bug in catching error in PromptTemplate's `is_concrete()` method

* Improvements to response inspector UI

* Ensured eval results (scores) are sorted alongside their responses the response inspector UI

* Removed response previews footer, replaced with Inspect responses button

* Prompt and eval nodes now load cached responses upon initialization

* Rebuilt React and raised package version
v0.1.7
2023-06-21 10:05:46 -04:00
ianarawjo
7fc0947d03
Update README.md 2023-06-19 20:39:01 -04:00
Ian Arawjo
d283cfdaf6 Bug fixes to queryLLM and merge responses 2023-06-17 09:34:23 -04:00
ianarawjo
70cba7aa3a
Update README.md 2023-06-16 12:33:17 -04:00
ianarawjo
8400b56f94
Change default boolean vis to be accuracy bar chart (#75) 2023-06-16 12:31:06 -04:00
Ian Arawjo
08bd734e96 Update xy pos of tabular nodes in oaievals v0.1.6 2023-06-15 15:48:49 -04:00
ianarawjo
1d08507c93
Load OpenAI evals as example flows (#74)
* Add OpenAI Evals tab to Example Flows pane.

* Add OpenAI evals examples (preconverted).

* Set unique IDs for each oaievals cforge file

* Use contenteditable divs in tables to improve performance.

* Update eval code to use json.loads instead of eval()

* Fix bug with $s in templates

* Update package info and point oaievals to main branch

* Made column headers use contenteditable p tags

* Add requests to dependency list

* Rebuilt react and updated package version
2023-06-15 15:41:58 -04:00
ianarawjo
655e1e6312
Add Azure OpenAI support (#72)
* Add OpenAI function calls to settings screen for Azure models, and backend support in the Azure call for functions and function_calls
v0.1.5.3
2023-06-13 18:01:24 -04:00
ianarawjo
e5b940b96b
Add basic support for OpenAI function calls (#73)
* Also includes start of categorical variables support in vis node

* Collapses same model responses (within `n` responses requested) and provides number of times they appeared

* Adds basic support for OpenAI function calls.

* Adds example flow illustrating OpenAI func calls
2023-06-13 17:33:15 -04:00
ianarawjo
caf8a3642b
Bug fix when inputing multiple vars from different prompt nodes into vis nodes (#70) 2023-06-12 12:06:38 -04:00
ianarawjo
947ca4b410
Update README.md 2023-06-11 13:02:59 -04:00
ianarawjo
3bfee02ec0
Add Tabular Data node and new Evaluator features to GUIDE.md v0.1.5 2023-06-11 12:19:04 -04:00
ianarawjo
30625bc527
Add tabular data example to README.md 2023-06-11 11:54:20 -04:00
ianarawjo
915f30988d
v0.1.5: Tabular Data Node, Evaluator Print Output (#66)
* Use Mantine Textarea controlled for Textfields node, instead of textarea

* Added Tabular data node

* TabularData context menus

* Make TabularData template hooks responsive to column name changes.

* Reduced spacing between template hooks

* Better table styling and rename column popup

* Add 'carry with' feature to Prompt Permutation recursive generation using `associate_id`

* Much nicer var tags on inspect window

* Nicer styling for LLM group headers in inspect screen

* Pass metavars around in the backend to surface them to front-end

* Set min-height on inspect node to be larger

* Added in-line print in Eval nodes

* Append error message to print output

* Minor inspect node CSS tweaks and fixes

* Removed mix-blend-mode due to performance issues scrolling large text

* Added ground truth eval example for math problems

* Updated React build and version number
2023-06-11 11:48:27 -04:00
ianarawjo
000b61200c
0.1.4: Failure Progress on Prompt Nodes, and others (#62)
* Lint Python code with ruff (#60)

* Failure progress on Prompt Nodes

* Change PromptNode preview container color

* Ensure LLM colors are unique and the same across nodes

* Reset LLM colors upon flow load

* Add LLM colors to 3D scatterplot

* Extract inspector internals into separate component. 

* Added inspect modal.

* Lower rate of failure for dummy LLM responses

* Fix useEffect bug in LLMResponseInspector

* Fix export to excel bug

* Remove dependence on browser support for regex negative lookbehind

* Use monospace font in textareas in Safari

* Fix settings modal bug in FireFox

* Change version

* Update README.md
v0.1.4
2023-06-07 20:36:55 -04:00
ianarawjo
c6da2314e7
Add Example flows pane and other minor improvements (#59)
* Example flows pane.

* Better Add+ Node UI.

* Added system message comparison example (see .

* Let user switch to gpt4 if initial model is gpt3.5
v0.1.3.1
2023-06-03 14:32:37 -04:00
ianarawjo
7eb5aaa26d
Model settings, more models, and visible temperature (#57)
* Model settings forms

* Editable nicknames and emojis

* Saving and loading model settings

* Temperature indicator on LLM items in PromptNodes

* Ensure LLM nicknames are unique

* Detect when PaLM blocks responses and output standard error msg in response instead

* Fix examples/ to use new cache format

* Add helpful 'could not reach server' text on countQueries fail

* Add Dalai model settings

* Rebuild react and update package version
v0.1.3
2023-06-01 15:08:17 -04:00