* added meilisearch retriever and credentials.ts
* added semantic ratio
* removed a TODO implementatio
* meilisearch component implemented with searching and upsert functionality (#3)
meilisearch retriever component created , searching for an existing index and upserting a new or existing index has been implemented , component utilizes langchain and meilisearch vector search
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/3
Reviewed-by: mohamed1999akram <mohamed1999akram@gmail.com>
* added CI/CD for ntg branch, added proper dockerfile for flowise-ntg (#4)
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/4
Reviewed-by: mohammad <mohammad@noreply.git.beyond.cc>
* modified os version , removed linting errors , removed cypress github actions (#5)
added --no-lock-file flag to pass CICD , made the runner run on debian and not ubuntu , removed code that caused warnings to pass linting
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/5
Reviewed-by: omaryassery <omarryassser@gmail.com>
* removed unnecessary QEMU install action (#6)
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/6
Reviewed-by: omaryassery <omarryassser@gmail.com>
* removed cypress installation and linting from dockerfile (#7)
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/7
Reviewed-by: isameh <isameh@ntgclarity.com>
* dockerfile-ntg-modification (#9)
dockerfile-ntg modified to copy all working directory before calling pnpm install
Reviewed-on: https://git.beyond.cc/ntg/flowise/pulls/9
Reviewed-by: isameh <isameh@ntgclarity.com>
* resolved comments, reverted CI/CD
* add test docker build yml back
* moved meilisearch to vector store folder
* Update Meilisearch.ts
---------
Co-authored-by: Henry <hzj94@hotmail.com>
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
* add langgraph
* datasource: initial commit
* datasource: datasource details and chunks
* datasource: Document Store Node
* more changes
* Document Store - Base functionality
* Document Store Loader Component
* Document Store Loader Component
* before merging the modularity PR
* after merging the modularity PR
* preview mode
* initial draft PR
* fixes
* minor updates and fixes
* preview with loader and splitter
* preview with credential
* show stored chunks
* preview update...
* edit config
* save, preview and other changes
* save, preview and other changes
* save, process and other changes
* save, process and other changes
* alpha1 - for internal testing
* rerouting urls
* bug fix on new leader create
* pagination support for chunks
* delete document store
* Update pnpm-lock.yaml
* doc store card view
* Update store files to use updated storage functions, Document Store Table View and other changes
* ui changes
* add expanded chunk dialog, improve ui
* change throw Error to InternalError
* Bug Fixes and removal of subFolder, adding of view chunks for store
* lint fixes
* merge changes
* DocumentStoreStatus component
* ui changes for doc store
* add remove metadata key field, add custom document loader
* add chatflows used doc store chips
* add types/interfaces to DocumentStore Services
* document loader list dialog title bar color change
* update interfaces
* Whereused Chatflow Name and Added chunkNo to retain order of created chunks.
* use typeorm order chunkNo, ui changes
* update tabler icons react
* cleanup agents
* add pysandbox tool
* add abort functionality, loading next agent
* add empty view svg
* update chatflow tool with chatId
* rename to agentflows
* update worker for prompt input values
* update dashboard to agentflows, agentcanvas
* fix marketplace use template
* add agentflow templates
* resolve merge conflict
* update baseURL
---------
Co-authored-by: vinodkiran <vinodkiran@usa.net>
Co-authored-by: Vinod Paidimarry <vinodkiran@outlook.in>
* Extend Confluence Document Loader to Support Server/Data Center with PAT
- Update authentication to use Personal Access Token (PAT)
- Expand compatibility to include both Confluence Cloud and Server/Data Center
* Update ConfluenceServerDCApi.credential.ts
* use the same confluence loader with different connection logic
* use the same confluence loader with different connection logic
* Apply Prettier formatting