Commit graph

115 commits

Author SHA1 Message Date
oleg cfaab0b829
fix(AWS Bedrock Chat Model Node): Improve filtering of Bedrock models & fix Claude 3 (#9085)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-04-09 14:22:48 +02:00
Michael Kret f62800cd72
fix: Continue on fail / error output support for chains and agents (#9078) 2024-04-09 15:06:12 +03:00
oleg 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 Prytoluk e47e4bf671
fix(Summarization Chain Node): 'Final Prompt to Combine' and 'Individual Summary Prompt' options (#8391) 2024-04-05 15:51:54 +02:00
कारतोफ्फेलस्क्रिप्ट™ 372d5c7d01
ci: Upgrade eslint, prettier, typescript, and some other dev tooling (no-changelog) (#8895)
Co-authored-by: Iván Ovejero <ivov.src@gmail.com>
2024-03-26 14:22:57 +01:00
oleg 76041b8587
fix(Anthropic Chat Model Node): Fix detection of chat models in docker build & add support Claude Haiku (#8953)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-03-22 12:03:54 +01:00
Michael Kret edce632ee6
fix: Validate custom tool names for forbidden chars (#8878) 2024-03-14 10:03:33 +02:00
Michael Kret 054a4fce1a
fix: OpenAI Node function to preserve original tools after node execution (#8872)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-03-13 18:13:15 +02:00
Michael Kret cef7c24b77
fix: OpenAI node text > message hide tools connector for unsupported models (#8866)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-03-12 17:23:00 +02:00
oleg 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
oleg a136a73e4e
feat: Update Pinecone Vector Store node to support serverless environments (#8849)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-03-08 16:01:02 +01:00
Giulio Andreini 5301323906
feat(editor): Improve errors in output panel (#8644)
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-03-07 18:08:01 +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
Jordan c8d589cce7
fix(GitHub Document Loader Node): Fix issue with ignore paths not working correctly (#8798) 2024-03-06 14:48:10 +00:00
Kate Mueller 3a7a6c8d6c
docs: Update OpenAI Node primaryDocumentation URL to match docs URL change (#8743) 2024-03-06 10:02:02 +00:00
oleg 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
Michael Kret e38e96bbec
fix(OpenAI Node): Message text operation parameters case fix (#8804) 2024-03-05 15:46:03 +02:00
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
Michael Kret 75e4df138f
fix: AI agents, throw error on duplicate names in dynamic tools (#8766)
Co-authored-by: oleg <me@olegivaniv.com>
2024-02-29 13:28:38 +02:00
Michael Kret 246bfb9ad4
feat: Chat Memory Manager group messages option, on insert delete return confirmation of success instead of messages (#8757) 2024-02-28 14:44:23 +02:00
Michael Kret 2aaf211dfc
feat: Session is selector for memory nodes (#8736) 2024-02-27 15:01:15 +02:00
Michael Kret 09524304e6
feat: SQL agent improvements (#8709)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-26 15:35:00 +02:00
कारतोफ्फेलस्क्रिप्ट™ 15490ad1d4
feat: Add support for Ollama embeddings API (#8732)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-26 14:20:18 +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
oleg d03d9276f9
feat(AI Agent Node): Allow use of Azure Chat model for OpenAI Functions agent (#8725)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-23 09:08:51 +01:00
Michael Kret 7c1cf33616
fix: Wrong prompt input key for sql agent (#8708) 2024-02-22 09:47:00 +02:00
oleg 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
oleg 40aecd1715
feat(AI Agent Node): Whitelist Azure Chat model for Agent (#8699)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-21 14:57:21 +01:00
कारतोफ्फेलस्क्रिप्ट™ 35245694b1
docs(OpenAI Node): Use the correct docs url (no-changelog) (#8693) 2024-02-21 14:47:56 +01:00
Michael Kret 1a81d0ad5f
fix(OpenAI Node): Remove require from text in assistant message (no-changelog) (#8658) 2024-02-16 15:23:42 +02:00
oleg e9af3e754f
fix(OpenAI Node): Always show jsonOutput toggle for OpenAI message operation (no-changelog) (#8651) 2024-02-16 09:31:53 +01:00
कारतोफ्फेलस्क्रिप्ट™ bf729aa2f0
refactor(editor): Do not use CodeNodeEditor anywhere except the Code node (no-changelog) (#8636) 2024-02-15 11:35:50 +01:00
Michael Kret 941278db68
feat(OpenAI Node): Overhaul (#8335) 2024-02-15 10:15:58 +02:00
Elias Meire 3b2078c3ca
fix(HTTP Request Node): Handle special characters in pagination expressions + improve hint text (#8576)
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-02-12 17:32:27 +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
Michael Kret ccc0ad5009
fix(core): Custom workflow tool tweaks (#8561) 2024-02-08 18:12:45 +02:00
Elias Meire de6d466e5e
refactor: Add lint rule for unsafe property access with lodash get/set (no-changelog) (#8587) 2024-02-08 15:32:04 +01:00
कारतोफ्फेलस्क्रिप्ट™ 8e392cfc1d
feat(core): Migrate to n8n's typeorm fork (#8590) 2024-02-08 15:13:29 +01:00
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 cccdfc73d6
fix(Embeddings OpenAI Node): Fix dynamic models fetching (#8533)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-02 12:27:13 +01:00
oleg 934d0d35b1
feat: Azure Open AI chat model & embeddings (#8522)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-02-01 16:48:18 +01:00
oleg 981ea3930e
feat: Add model parameter to OpenAI embeddings (#8481)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-01-29 16:34:23 +01:00
कारतोफ्फेलस्क्रिप्ट™ 3cc0f81c02
docs: Update MemoryChatRetriever docs url (no-changelog) (#8455) 2024-01-26 12:04:51 +01:00
Tomi Turtiainen 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
Deborah c8a2fe05d2
docs: Update link in manual chat trigger node (no-changelog) (#8328) 2024-01-15 11:54:32 +00:00
oleg 464be93323
feat: Implement Chat Memory Manager node (#8127)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-01-15 10:13:54 +02:00
oleg 851060dd3f
fix: Add fallback resolver for langchain modules (#8308)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2024-01-12 18:33:33 +01:00
oleg c2748802a2
ci: Add @aws-sdk/credential-provider-node and @aws-sdk/types modules (no-changelog) (#8310)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Jan Oberhauser <jan.oberhauser@gmail.com>
2024-01-11 18:46:21 +01:00
Deborah 90404a4b88
docs: Update links in deprecated langchain nodes to avoid linting errors (no-changelog) (#8273) 2024-01-09 14:50:00 +01:00
Alex Grozav 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
oleg d37b9084b2
feat: Implement MistralCloud Chat & Embeddings nodes (#8239)
Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Michael Kret <michael.k@radency.com>
2024-01-08 16:17:55 +01:00
Anush 66460f66b0
feat(Qdrant Vector Store Node): Qdrant vector store support (#8080)
## Summary
This PR intends to add [Qdrant](https://qdrant.tech/) as a supported
vectorstore node to load and retrieve documents from in a workflow.


## Review / Merge checklist
- [x] PR title and summary are descriptive. 
- [x] Node/credentials documentation to be updated in
https://github.com/n8n-io/n8n-docs/pull/1796.

---------

Co-authored-by: oleg <me@olegivaniv.com>
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
2024-01-03 11:14:51 +01:00
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
कारतोफ्फेलस्क्रिप्ट™ 216ec079c9
feat(editor): Create separate components for JS and JSON editors (no-changelog) (#8156)
## Summary
This is part-1 of refactoring our code editors to extract different type
of editors into their own components.
In part-2 we'll
1. delete a of unused or duplicate code
2. switch to a `useEditor` composable to bring more UX consistency
across all the code editors.

## Review / Merge checklist
- [x] PR title and summary are descriptive
- [x] Tests included
2023-12-29 10:49:27 +01:00
Jan Oberhauser bec0faed9e
feat(core): Add closeFunction support to Sub-Nodes (#7708)
Github issue / Community forum post (link here to close automatically):

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: Oleg Ivaniv <me@olegivaniv.com>
2023-12-21 14:21:09 +01:00
oleg 7806a65229
feat: Add option to returnIntermediateSteps for AI agents (#8113)
## Summary
![CleanShot 2023-12-21 at 08 30
16](https://github.com/n8n-io/n8n/assets/12657221/66b0de47-80cd-41f9-940e-6cacc2c940a9)

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2023-12-21 10:27:49 +01:00
Deborah f432d86524
docs: Two small UI copy fixes in sub-nodes (#8032) 2023-12-14 19:15:38 +00:00
Elias Meire 8a5343401d
feat(editor): Filter component + implement in If node (#7490)
New Filter component + implementation in If node (v2)

<img width="3283" alt="image"
src="https://github.com/n8n-io/n8n/assets/8850410/35c379ef-4b62-4d06-82e7-673d4edcd652">

---------

Co-authored-by: Giulio Andreini <andreini@netseven.it>
Co-authored-by: Michael Kret <michael.k@radency.com>
2023-12-13 14:45:22 +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
Iván Ovejero 8cb9c6b3ea
ci: Introduce no-plain-errors lint rule for BE packages (no-changelog) (#7961)
## Summary
Require `ApplicationError` or its child classes instead of plain `Error`
in BE packages. This ensures the error will be normalized when reported
to Sentry, if applicable.

Follow-up to:
https://github.com/n8n-io/n8n/pulls?q=is%3Apr+is%3Aclosed+applicationerror

...

#### How to test the change:
1. ...


## 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

...


## Review / Merge checklist
- [ ] 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))
- [ ] [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).
2023-12-08 12:51:49 +01:00
oleg e4ae11c2ad
fix: Remove Tensorflow embeddings node (no-changelog) (#7922)
## Summary
This PR removes `embeddingsTensorFlow` node and reverts our fix to
accommodate the Docker build in #7893 .
The node itself has been extracted as a [community node available from
npm](https://www.npmjs.com/package/n8n-nodes-tensorflow)

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
2023-12-04 17:48:10 +01:00
Deborah 485a0c73cb
docs: Fix typo in tooltip relating to JMESPath (#7910) 2023-12-04 08:19:36 +00:00
Iván Ovejero b024cc52e7
ci: Fix lint warnings in @n8n/chat and @n8n/nodes-langchain (no-changelog) (#7884)
Solve lint warnings shown on all PRs for `@n8n/chat` and
`@n8n/nodes-langchain`

Example: https://github.com/n8n-io/n8n/pull/7883/files
2023-11-30 13:22:27 +01:00
oleg e834f14991
refactor: Remove Epub document loader override (no-changelog) (#7874)
- Remove Epub document loader override, use standard Langchain loader
- Use temporary buffer file for document loader processing and pass just
the path
- Remove replace `@gxl/epub-parser` library with `epub2`

Github issue / Community forum post (link here to close automatically):

---------

Signed-off-by: Oleg Ivaniv <me@olegivaniv.com>
Co-authored-by: कारतोफ्फेलस्क्रिप्ट™ <aditya@netroy.in>
2023-11-30 11:59:37 +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