Siddharth Chauhan
0cc7b3036e
fix: Upgrade Hugging Face Inference API to support Inference Providers ( #5454 )
...
- Upgrade @huggingface/inference from v2.6.1 to v4.13.2
- Update ChatHuggingFace to use InferenceClient with chatCompletion API
- Update HuggingFaceInference (LLM) to use v4 HfInference with Inference Providers
- Update HuggingFaceInferenceEmbedding to use v4 HfInference
- Add endpoint handling logic to ignore custom endpoints for provider-based models
- Add improved error handling and validation for API keys
- Update UI descriptions to guide users on proper configuration
Fixes #5161
Co-authored-by: Henry <hzj94@hotmail.com>
2025-11-25 11:43:36 +00:00
Luis Felipe Salazar Ucros
bf1ddc3be5
Feature: Add SambaNova ( #4961 )
...
* add sambanova
* add sambanova credential
* fix samba nova chat node
---------
Co-authored-by: Henry <hzj94@hotmail.com>
2025-08-18 22:09:39 +08:00
Karl Stoney
00342bde88
Refactor google credentials into a shared function ( #4893 )
2025-07-24 20:06:30 +01:00
Henry Heng
5a37227d14
Chore/refractor ( #4454 )
...
* markdown files and env examples cleanup
* components update
* update jsonlines description
* server refractor
* update telemetry
* add execute custom node
* add ui refractor
* add username and password authenticate
* correctly retrieve past images in agentflowv2
* disable e2e temporarily
* add existing username and password authenticate
* update migration to default workspace
* update todo
* blob storage migrating
* throw error on agent tool call error
* add missing execution import
* add referral
* chore: add error message when importData is undefined
* migrate api keys to db
* fix: data too long for column executionData
* migrate api keys from json to db at init
* add info on account setup
* update docstore missing fields
---------
Co-authored-by: chungyau97 <chungyau97@gmail.com>
2025-05-27 07:29:42 +01:00
Henry Heng
a0b4abdd13
Feature/update openai version, add reasoning effort param, add o3 mini ( #3973 )
...
* update openai version, add reasoning effort param
* update azure
* add filter for pinecone llamaindex
* update graph cypher qa chain
2025-02-04 08:43:27 +00:00
Eduard-Constantin Ibinceanu
99d4bacd8a
IBM Watsonx LLM node ( #3674 )
...
* Add node icon
* Add node
2024-12-11 10:42:49 +00:00
Henry Heng
940c8fd3b0
Chore/LC v0.3 ( #3517 )
...
* bump langchain version to 0.3, upgrades on all chat models
* update all docs loader to have documents and text output options
* fix pnpm lock file
2024-11-28 11:06:12 +00:00
Jérémy JOURDIN
012eabc996
[Azure OpenAI] Make credentials optional when env variables are set ( #3418 )
...
* Make Azure OpenAI credentials optional when env variables are set
* Add documentation for env vars
2024-11-01 22:09:13 +00:00
Henry Heng
d1da628b7c
Feature/Add base path to azure ( #2984 )
...
add base path to azure
2024-08-09 14:28:52 +01:00
Henry Heng
bca4de0c63
Feature/seq agents ( #2798 )
...
* update build functions
* sequential agents
* update langchain to 0.2, added sequential agent nodes
* add marketplace templates
* update howto wordings
* Merge branch 'main' into feature/Seq-Agents
# Conflicts:
# pnpm-lock.yaml
* update deprecated functions and add new sequential nodes
* add marketplace templates
* update marketplace templates, add structured output to llm node
* add multi agents template
* update llm node with bindmodels
* update cypress version
* update templates sticky note wordings
* update tool node to include human in loop action
* update structured outputs error from models
* update cohere package to resolve google genai pipeThrough bug
* update mistral package version, added message reconstruction before invoke seq agent
* add HITL to agent
* update state messages restructuring
* update load and split methods for s3 directory
2024-07-22 17:46:14 +01:00
jiabaow
6fb775fe95
add Fireworks LLM ( #2597 )
...
* add Fireworks LLM
* support multiple models
* Update Fireworks.ts
* fix linting
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
2024-06-11 21:56:34 +01:00
jiabaow
50c53de296
Together AI llms ( #2454 )
...
* add TogetherAI.ts skeleton
* add TogetherAI api links
* fix constructing final obj
* fix INodeData import
* fix category
* fix version & streaming
* add stop
* update constructor
* update constructor with default values
* add togetherAI logo
* add credential
* change logo
* update streaming
* disable streaming
* remove model
* clean up comment
* delete unused icon
* add togetherAI for streaming
* Update index.ts
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
2024-05-24 01:22:41 +01:00
Vinod Kiran
788d40f26b
Feature/externalize model list ( #2113 )
...
* fixes
* test json
* test json
* externalize model list
* externalize model list
* correcting awsChatBedRock Name
* lint fixes
* externalize models
* externalize chat models
* externalize chat models
* externalize llm models
* externalize llm models
* lint fixes
* addition of models for ChatMistral
* updating version numbers for all imapacted nodes.
* marketplace template updates
* update embeddings, marketplaces, add chatCohere
* config changes for new env variable
* removal of local models.json
* update models json file
---------
Co-authored-by: Henry <hzj94@hotmail.com>
2024-04-12 12:46:10 +01:00
Henry
c557d8d19c
update pnpm wordings
2024-03-12 16:53:20 +08:00
Ilango
7313891ea1
Fix merge conflict
2024-03-12 12:46:25 +05:30
vinodkiran
20929dbff1
bugfix - fix for inccorect bedrock imports
2024-03-10 21:31:39 +05:30
Ilango
e3b5309855
Fix merge conflicts
2024-03-06 16:03:12 +05:30
Henry
0606d2c6dd
upgrade langchain version 0.1.0
2024-01-26 23:41:55 +00:00
Darien Kindlund
61e1866615
Added support for gpt-4 and gpt-4-32k models
2024-01-23 17:53:57 -05:00
Henry
75b5b33d8d
update langchain version
2023-12-30 12:29:00 +00:00
abhishekshankr
8cf34dfda8
Fix file extension
2023-12-21 12:04:48 -05:00
abhishekshankr
d67cf332d8
Update icons
2023-12-21 11:57:09 -05:00
Henry Heng
c636a9c914
Merge pull request #1407 from abhishekshankr/UI/Custom-Icons
...
UI/Custom Icons for Nodes
2023-12-19 23:35:37 +00:00
abhishekshankr
4ce79acdf6
Update OpenAI Icons
2023-12-19 17:52:50 -05:00
Henry
7952ef8df5
fix bedrock model empty bug
2023-12-19 01:31:09 +00:00
abhishekshankr
bc459df067
Updated icons
2023-12-18 12:52:27 -05:00
abhishekshankr
c079781d18
Updated embeddings and llm icons
2023-12-18 03:30:07 -05:00
Henry
6e4822c3bb
update bedrock
2023-12-15 17:49:29 +00:00
Henry
4e3f219e2d
update readme and vite port
2023-11-27 12:24:11 +00:00
Henry
12c688aae0
update langchain version
2023-11-24 14:29:50 +00:00
Henry Heng
0e2cba03cc
Merge pull request #1034 from FlowiseAI/feature/BedrockEmbeddings
...
Feature/AWSBedrock embeddings
2023-10-11 14:33:13 +01:00
Henry
536ed07f9d
add bedrock embeddings
2023-10-11 14:08:04 +01:00
Henry
cf9e3499a7
add ollama
2023-10-11 12:24:06 +01:00
vinodkiran
7d4337724d
Updating of Type LLMCache to BaseCache and renaming vars for clarity
2023-10-08 22:59:43 +05:30
Henry Heng
91581250a7
Merge branch 'main' into FEATURE/llm-cache
2023-10-06 19:04:24 +01:00
Brian Krygsman
ca6b0f2b22
Add AWS Bedrock LLM support.
...
Note: stop sequences parameter not yet implemented.
2023-10-02 08:50:17 -04:00
vinodkiran
d81869fd59
Extending support for Caching to all LLM's.
2023-09-29 08:19:44 +05:30
vinodkiran
d588ac0480
Adding support for LLM Caching.
2023-09-29 07:54:16 +05:30
BitVoyagerMan
37d8b3f310
fix lint
2023-09-21 07:12:28 -04:00
BitVoyagerMan
50903453f0
add bittensor chatmodel
2023-09-21 02:40:55 -04:00
Henry
096451f82f
update langchain version
2023-09-20 20:07:13 +01:00
Henry
4682be5c03
update openai models
2023-09-19 11:53:16 +01:00
Martin Andrews
19824bf339
Moved APIkey helper text, and fixed linter complaints
2023-09-06 08:41:12 +00:00
Martin Andrews
e5167f3e20
First draft of PaLM API LLM component
2023-09-05 18:43:14 +00:00
Yongtae
4d8b24180c
add 32k model
2023-09-03 19:27:00 +09:00
Henry
c25eaa1139
add chatOpenAI Finetuned
2023-08-28 13:11:15 +01:00
Yongtae
9dff0646ce
adopt optional credential on LLM
2023-08-25 16:47:44 +09:00
Yongtae
495919a1d8
Revert "implementation of embedding model"
...
This reverts commit 0830b8fbe5 .
2023-08-25 00:40:25 +09:00
Yongtae
d9113da6bb
lint fix
2023-08-24 11:42:49 +09:00
Yongtae
0830b8fbe5
implementation of embedding model
2023-08-24 11:39:22 +09:00