Commit graph

18 commits

Author SHA1 Message Date
Michael Kret a6a5372b5f
fix(OpenAI Node): Load correct models for operation (#8313) 2024-01-15 15:13:38 +02:00
Michael Kret 5e16dd4ab4
feat(core): Improvements/overhaul for nodes working with binary data (#7651)
Github issue / Community forum post (link here to close automatically):

---------

Co-authored-by: Giulio Andreini <andreini@netseven.it>
Co-authored-by: Marcus <marcus@n8n.io>
2024-01-03 13:08:16 +02:00
Iván Ovejero 0ca2759d75
refactor: Optimize SVG icons for nodes (#8195)
Running `svgo` to optimize icon size for nodes.
2024-01-02 17:40:08 +01:00
oleg dcf12867b3
feat: AI nodes usability fixes + Summarization Chain V2 (#7949)
Fixes:
- Refactor connection snapping when dragging and enable it also for
non-main connection types
- Fix propagation of errors from sub-nodes
- Fix chat scrolling when sending/receiving messages
- Prevent empty chat messages
- Fix sub-node selected styles
- Fix output names text overflow

Usability improvements:
- Auto-add manual chat trigger for agents & chain nodes
- Various labels and description updates
- Make the output parser input optional for Basic LLM Chain
- Summarization Chain V2 with a simplified document loader & text
chunking mode

#### How to test the change:
Example workflow showcasing different operation mode of the new
summarization chain:

[Summarization_V2.json](https://github.com/n8n-io/n8n/files/13599901/Summarization_V2.json)


## Issues fixed
Include links to Github issue or Community forum post or **Linear
ticket**:
> Important in order to close automatically and provide context to
reviewers
-
https://www.notion.so/n8n/David-Langchain-Posthog-notes-7a9294938420403095f4508f1a21d31d
- https://linear.app/n8n/issue/N8N-7070/ux-fixes-batch
- https://linear.app/n8n/issue/N8N-7071/ai-sub-node-bugs


## Review / Merge checklist
- [x] PR title and summary are descriptive. **Remember, the title
automatically goes into the changelog. Use `(no-changelog)` otherwise.**
([conventions](https://github.com/n8n-io/n8n/blob/master/.github/pull_request_title_conventions.md))
- [x] [Docs updated](https://github.com/n8n-io/n8n-docs) or follow-up
ticket created.
- [ ] Tests included.
> A bug is not considered fixed, unless a test is added to prevent it
from happening again. A feature is not complete without tests.
  >
> *(internal)* You can use Slack commands to trigger [e2e
tests](https://www.notion.so/n8n/How-to-use-Test-Instances-d65f49dfc51f441ea44367fb6f67eb0a?pvs=4#a39f9e5ba64a48b58a71d81c837e8227)
or [deploy test
instance](https://www.notion.so/n8n/How-to-use-Test-Instances-d65f49dfc51f441ea44367fb6f67eb0a?pvs=4#f6a177d32bde4b57ae2da0b8e454bfce)
or [deploy early access version on
Cloud](https://www.notion.so/n8n/Cloudbot-3dbe779836004972b7057bc989526998?pvs=4#fef2d36ab02247e1a0f65a74f6fb534e).

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Elias Meire <elias@meire.dev>
2023-12-08 13:42:32 +01:00
Jon a9c7188c4d
feat(OpenAI Node): Add dall-e-3 support (#7655)
Adds support for dall-e-3 under Image
Removes GPT 4 Vision from Chat completion for now
Cleans up Model list for text completion by removing dall-e and tts
2023-11-14 10:34:45 +00:00
Iván Ovejero 24ce141815
refactor: Clear unused ESLint directives from nodes-base (no-changelog) (#6812)
* refactor: Clear unused ESLint directives from nodes-base (no-changelog)

* removed unused disable directives

---------

Co-authored-by: Marcus <marcus@n8n.io>
2023-08-01 15:32:33 +02:00
MC Naveen 26046f6fe8
feat(OpenAI Node): Update max token limit to support newer model limits (#6644) 2023-07-12 12:38:54 +01:00
Michael Kret 8fdfa3b6b8
fix(OpenAI Node): Descriptive errors (#6270) 2023-05-18 17:20:56 +03:00
Eddy Hernandez 6b9909bd80
fix(OpenAI Node): Update OpenAI Text Moderate input placeholder text (#5823) 2023-04-17 16:03:34 +01:00
Jon 29959be688
fix(OpenAI Node): Update models to only show those supported (#5805) 2023-04-12 16:07:35 +02:00
Jon ba73fff27d
feat(OpenAI Node): Add support for gpt4 on chat completion (#5692) 2023-03-15 09:41:02 +00:00
Jan Oberhauser 1c65bff31d
fix(OpenAI Node): Simplify code (#5618)
fix(OpenAI Node): Simplifiy code
2023-03-05 17:43:17 +01:00
Jon e949db3525
fix(OpenAI Node): Fix issue with expressions not working with chat complete (#5609) 2023-03-03 16:08:12 +00:00
Jon 06c5ecbdf3
feat(OpenAI Node): Add support for ChatGPT (#5596) 2023-03-02 14:17:29 +00:00
Ashish Ahuja 04c058a34e
feat(OpenAI Node): Add frequency-penalty and presence-penalty (#5137) 2023-02-02 12:18:11 +00:00
Iván Ovejero b03e358a12
refactor: Integrate consistent-type-imports in nodes-base (no-changelog) (#5267)
* 👕 Enable `consistent-type-imports` for nodes-base

* 👕 Apply to nodes-base

*  Undo unrelated changes

* 🚚 Move to `.eslintrc.js` in nodes-base

*  Revert "Enable `consistent-type-imports` for nodes-base"

This reverts commit 529ad72b05.

* 👕 Fix severity
2023-01-27 12:22:44 +01:00
Deborah 37b1e079ea
docs: Add correct URL for credentials doc to OpenAI node (#4961)
add correct URL for credentials doc
2022-12-19 13:18:37 +01:00
Jan Oberhauser 7a984bb6b7
feat(OpenAI Node): Add a node to work with OpenAI (#4932)
* feat(OpenAI Node): Add a node to work with OpenAI

* Added codex file for OpenAi node

* Minor tweaks to Operation Image.

* Minor tweaks to Resource Text.

* Minor copy modification to Image:Create.

* Removed "a Text" in Text operations names.

*  Connect Response Format parameter and other improvements

*  Add "filter" postReceiveAction

*  Rename operations and add spelling mistake again to example

*  Rename another operation

Co-authored-by: Jonathan Bennetts <jonathan.bennetts@gmail.com>
Co-authored-by: Giulio Andreini <andreini@netseven.it>
2022-12-16 01:05:42 +01:00