|
f3e29d25ed
|
feat: Optimize langchain calls in batching mode (#15011)
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
|
2025-05-02 17:09:31 +02:00 |
|
|
Benjamin SchrothandGitHub
|
9021e195fa
|
fix(Text Classifier Node): Validate inputText parameter (#14832)
|
2025-04-23 14:18:36 +02:00 |
|
|
olegandGitHub
|
bbd6e8ee41
|
fix(Basic LLM Chain Node): Prevent stringifying of structured output on previous versions (#14200)
|
2025-03-27 11:48:17 +01:00 |
|
|
olegandGitHub
|
b9030d45de
|
fix(Basic LLM Chain Node): Prevent incorrect wrapping of output (#14183)
|
2025-03-26 14:26:09 +01:00 |
|
|
Charlie KolbandGitHub
|
70764a0258
|
fix: Correct connections in SentimentAnalysis and TextClassifier (#14155)
|
2025-03-25 09:08:33 +01:00 |
|
|
|
8215e0b59f
|
refactor: Migrate NodeConnectionType to const object type (no-changelog) (#14078)
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
|
2025-03-21 14:01:26 +02:00 |
|
|
Alex GrozavandGitHub
|
49872fbbac
|
fix: Replace ai nodes enum strings with hard-coded values (no-changelog) (#14091)
|
2025-03-21 09:24:05 +02:00 |
|
|
olegandGitHub
|
1bfd128717
|
refactor(Basic LLM Chain Node): Refactor Basic LLM Chain & add tests (#13850)
|
2025-03-14 11:38:22 +01:00 |
|
|
EugeneandGitHub
|
311553926a
|
refactor(Question and Answer Chain Node): Use new LangChain's syntax (#13868)
|
2025-03-14 11:17:11 +01:00 |
|
|
Jaakko HussoandGitHub
|
4fa666b976
|
feat(editor): Rename 'Text' fields on AI nodes to 'Prompt' (#13416)
|
2025-02-21 18:38:14 +02:00 |
|
|
olegandGitHub
|
47c5688618
|
fix(AI Agent Node): Move model retrieval into try/catch to fix continueOnFail handling (#13165)
|
2025-02-13 15:47:41 +01:00 |
|
|
Charlie KolbandGitHub
|
11cf1cd23a
|
feat(editor): Expose View Execution links for erroneous sub-executions (#13185)
|
2025-02-13 09:44:52 +01:00 |
|
|
|
02573b46e0
|
feat(core): Add error reporting for workflow evaluation (no-changelog) (#12838)
Co-authored-by: oleg <me@olegivaniv.com>
|
2025-02-11 16:03:41 +01:00 |
|
|
jeanpaulandGitHub
|
2b1eb049f2
|
fix(Basic LLM Chain Node): Use correct mimetype for binary data (#12978)
|
2025-02-07 09:49:11 +01:00 |
|
|
EugeneandGitHub
|
01b781a108
|
fix(editor): Nodes' icon color in dark mode (#12279)
|
2024-12-19 13:05:12 +01:00 |
|
|
कारतोफ्फेलस्क्रिप्ट™andGitHub
|
2ce1644d01
|
refactor(core): Shovel around more of AI code (no-changelog) (#12218)
|
2024-12-16 13:46:19 +01:00 |
|
|
olegandGitHub
|
565f8cd8c7
|
feat(editor): Improve how we show default Agent prompt and Memory session parameters (#11491)
|
2024-11-12 11:33:20 +01:00 |
|
|
olegandGitHub
|
45274f2e7f
|
feat(Structured Output Parser Node): Refactor Output Parsers and Improve Error Handling (#11148)
|
2024-10-22 10:46:58 +02:00 |
|
|
Tomi TurtiainenandGitHub
|
a042d5c8e6
|
refactor: Replace json-schema-to-zod with our own fork (#11229)
|
2024-10-18 09:29:19 +03:00 |
|
|
Tomi TurtiainenandGitHub
|
2bb1996738
|
feat: Add once for each item support for JS task runner (no-changelog) (#11109)
|
2024-10-07 21:18:32 +03:00 |
|
|
EugeneandGitHub
|
77fec195d9
|
fix(Text Classifier Node): Default system prompt template (#11018)
|
2024-09-30 15:07:20 +02:00 |
|
|
Miguel PrytolukandGitHub
|
08a27b3148
|
feat(Question and Answer Chain Node): Customize question and answer system prompt (#10385)
|
2024-09-27 12:09:39 +02:00 |
|
|
EugeneandGitHub
|
ab83c4b416
|
fix(OpenAI Node, Basic LLM Chain Node, Tool Agent Node): Better OpenAI API rate limit errors (#10797)
|
2024-09-18 10:52:10 +02:00 |
|
|
EugeneandGitHub
|
aa37c32f26
|
feat(Text Classifier Node): Add output fixing parser (#10667)
|
2024-09-05 09:39:44 +02:00 |
|
|
Michael KretandGitHub
|
9fa1a9aa99
|
fix: Disable errors obfuscation (no-changelog) (#10617)
|
2024-08-30 10:59:30 +03:00 |
|
|
Iván OvejeroandGitHub
|
bc958be93b
|
refactor(core): Convert verbose to debug logs (#10574)
|
2024-08-28 09:32:53 +02:00 |
|
|
jeanpaulandGitHub
|
452f52c124
|
fix(Text Classifier Node): Use proper documentation URL and respect continueOnFail (#10216)
|
2024-07-30 16:19:47 +02:00 |
|
|
olegandGitHub
|
5a51b1db5e
|
refactor: Update Langchain modules & add Ollama tools support (#10208)
|
2024-07-26 14:30:33 +02:00 |
|
|
olegandGitHub
|
8ef0a0c58a
|
feat(Sentiment Analysis Node): Implement Sentiment Analysis node (#10184)
|
2024-07-26 13:19:06 +02:00 |
|
|
EugeneandGitHub
|
3d235b0b2d
|
feat(Information Extractor Node): Add new simplified AI-node for information extraction (#10149)
|
2024-07-25 14:47:18 +02:00 |
|
|
jeanpaulandGitHub
|
12d692349d
|
refactor(Text Classifier Node): Mark the text classifier node as black (#10118)
|
2024-07-19 14:51:03 +02:00 |
|
|
jeanpaulandGitHub
|
fd833ec079
|
feat(Text Classifier Node): Change fallback option to a drop-down (no-changelog) (#10039)
|
2024-07-12 17:11:08 +02:00 |
|
|
|
28ca7d6a2d
|
feat(Text Classifier Node): Add Text Classifier Node (#9997)
Co-authored-by: oleg <me@olegivaniv.com>
|
2024-07-11 16:24:03 +02:00 |
|
|
|
b7aea957b8
|
feat: Do not show errors not processed by n8n (no-changelog) (#9598)
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
|
2024-06-20 08:45:00 +03:00 |
|
|
olegandGitHub
|
be4f54de15
|
feat(editor): Node Creator AI nodes improvements (#9484)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2024-05-30 16:53:33 +02:00 |
|
|
|
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 |
|
|
कारतोफ्फेलस्क्रिप्ट™andGitHub
|
2bdc459bb2
|
refactor(core): Fix type errors in workflow, core, nodes-langchain, and nodes-base (no-changelog) (#9450)
|
2024-05-22 17:40:52 +02:00 |
|
|
|
e17e767e70
|
feat(Ollama Chat Model Node): Add aditional Ollama config parameters & fix vision (#9215)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
|
2024-04-29 13:41:48 +02:00 |
|
|
|
f1215cdb6b
|
feat(Google Gemini Chat Model Node): Add support for new Google Gemini models (#9130)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
|
2024-04-15 13:56:44 +02:00 |
|
|
Michael KretandGitHub
|
f62800cd72
|
fix: Continue on fail / error output support for chains and agents (#9078)
|
2024-04-09 15:06:12 +03:00 |
|
|
olegandGitHub
|
936682eeaa
|
feat(core): Improve Langsmith traces for AI executions (#9081)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2024-04-08 22:51:49 +02:00 |
|
|
Miguel PrytolukandGitHub
|
e47e4bf671
|
fix(Summarization Chain Node): 'Final Prompt to Combine' and 'Individual Summary Prompt' options (#8391)
|
2024-04-05 15:51:54 +02:00 |
|
|
olegandGitHub
|
a3a931bdd1
|
fix(editor): Do not throw an error when calculating dynamic inputs/outputs (no-changelog) (#8858)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2024-03-11 10:34:59 +01:00 |
|
|
|
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 |
|
|
olegandGitHub
|
82f66c87e0
|
fix(Basic LLM Chain Node): Fix retrieving of prompt parameter for v1.3 of the node (#8817)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
|
2024-03-05 17:43:24 +01:00 |
|
|
|
2068f186ff
|
feat: Introduce prompt type option for Agent, Basic LLM Chain, and QA Chain nodes (#8697)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
|
2024-02-21 14:59:37 +01:00 |
|
|
olegandGitHub
|
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 |
|
|
|
9a1cc56806
|
fix: Set '@typescript-eslint/return-await' rule to 'always' for node code (no-changelog) (#8363)
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
|
2024-01-17 17:08:50 +02:00 |
|
|
+4
|
af49e95cc7
|
feat: Add Chat Trigger node (#7409)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Jan Oberhauser <jan.oberhauser@gmail.com>
Co-authored-by: Jesper Bylund <mail@jesperbylund.com>
Co-authored-by: OlegIvaniv <me@olegivaniv.com>
Co-authored-by: Deborah <deborah@starfallprojects.co.uk>
Co-authored-by: Jan Oberhauser <janober@users.noreply.github.com>
Co-authored-by: Jon <jonathan.bennetts@gmail.com>
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
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>
|
2024-01-09 13:11:39 +02:00 |
|
|
|
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 |
|