Commit graph

17 commits

Author SHA1 Message Date
कारतोफ्फेलस्क्रिप्ट™ 8f5fe05a92
refactor(core): All calls to supplyData should use a distinct context type (no-changelog) (#11421) 2024-10-28 11:37:23 +01:00
oleg 45274f2e7f
feat(Structured Output Parser Node): Refactor Output Parsers and Improve Error Handling (#11148) 2024-10-22 10:46:58 +02:00
Iván Ovejero c133a6ef89
refactor(core): Include AI events in log streaming relay (#10768) 2024-09-12 12:02:47 +02:00
Ricardo Espinoza c4eb3746d7
refactor: Use NodeConnectionType consistently across the code base (no-changelog) (#10595) 2024-08-29 09:55:53 -04:00
oleg 9cbbb6335d
feat(Postgres Chat Memory Node): Implement Postgres Chat Memory node (#10071) 2024-07-17 08:25:37 +02:00
Eugene 071130a2dc
feat(Google Vertex Chat Model Node): Add support for Google Vertex AI Chat models (#9970)
Co-authored-by: oleg <oleg@n8n.io>
2024-07-11 14:41:10 +02:00
कारतोफ्फेलस्क्रिप्ट™ a77e8dd79e
feat(core): Upgrade all langchain related dependencies (#9504)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-05-24 14:43:17 +02:00
oleg 677f534661
feat(AI Agent Node): Implement Tool calling agent (#9339)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-05-15 12:02:21 +02:00
oleg 359ade45bc
refactor: Implement LLM tracing callback to improve parsing of tokens usage stats (#9311)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-05-12 21:12:07 +02:00
oleg 0f7ae3f50a
refactor: Update Langchain to 0.1.41 & add support for Claude 3 (#8825)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-03-07 11:36:36 +01:00
oleg bfda8ead0c
fix(editor): Fix retrieving of messages from memory in chat modal (#8807)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-03-05 13:53:46 +01:00
oleg 7d82dc1ea8
fix: Simplify Structured Output Parser wrapping and fix auto-fixing output parser (#8778)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-03-01 08:41:45 +01:00
oleg 0882dc0ce9
fix: Fix execution error when using AI chain nodes with non-chat model (#8724)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-23 10:27:39 +01:00
Omar Ajoue 7501ad8f3c
feat: Add support for AI log streaming (#8526)
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-09 09:41:01 +00:00
oleg c8b8379015
fix: Update BaseChatModel import checks for MistralAI compatibility (#8527)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-05 16:09:23 +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
Jan Oberhauser 87def60979
feat: Add AI tool building capabilities (#7336)
Github issue / Community forum post (link here to close automatically):
https://community.n8n.io/t/langchain-memory-chat/23733

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Val <68596159+valya@users.noreply.github.com>
Co-authored-by: Alex Grozav <alex@grozav.com>
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
Co-authored-by: Deborah <deborah@starfallprojects.co.uk>
Co-authored-by: Jesper Bylund <mail@jesperbylund.com>
Co-authored-by: Jon <jonathan.bennetts@gmail.com>
Co-authored-by: Michael Kret <88898367+michael-radency@users.noreply.github.com>
Co-authored-by: Giulio Andreini <andreini@netseven.it>
Co-authored-by: Mason Geloso <Mason.geloso@gmail.com>
Co-authored-by: Mason Geloso <hone@Masons-Mac-mini.local>
Co-authored-by: Mutasem Aldmour <mutasem@n8n.io>
2023-11-29 12:13:55 +01:00