Skip to content

Releases: cloudera/CML_AMP_RAG_Studio

1.26.0-beta

30 Jul 20:00
3ea735d
Compare
Choose a tag to compare
1.26.0-beta Pre-release
Pre-release
Add script for restoring the global summary index (#281)

* Add script for restoring the global summary index

* Clarify run directions

* Remove irrelevant change

* Remove irrelevant change

* Satisfy linters

1.25.0

14 Jul 23:15
7d98ef9
Compare
Choose a tag to compare
Chat UI improvements (#270)

* move select a datasource

* fix search

* fix spacing in input

* width

* add inference model selection to the chat input

* fix broken test

* handle showing correct model before activeSession

* handle tool calling enablement based on inference model

* adjust width of options

* fix up broken things, and provide models for projects to the chat initiator

* adjust colors

* capitalize

* bug fix for retriever tool with no summaries

* fix broken tests

* split bedrock by model family

---------

Co-authored-by: Elijah Williams <[email protected]>
Co-authored-by: Baasit Sharief <[email protected]>

1.24.1

11 Jul 15:46
6fe1325
Compare
Choose a tag to compare
fix bug with empty kb (#263)

* fix bug with empty kb

* Update llm-service/app/services/query/querier.py

Co-authored-by: Copilot <[email protected]>

* small tweak

---------

Co-authored-by: Copilot <[email protected]>

1.24.0

09 Jul 17:36
b168300
Compare
Choose a tag to compare
revert mlflow to 2.x version and update run_uuid key (#259)

* revert mlflow to 2.x version and update run_uuid key

* pin mlflow to 2.22.1

---------

Co-authored-by: Elijah Williams <[email protected]>

1.24.0-beta

09 Jul 16:59
1454207
Compare
Choose a tag to compare
1.24.0-beta Pre-release
Pre-release
Upload files to a chat (#256)

* make the indexing reconciler request summarization immediately after each file is complete

* immediately submit docs for summarization on upload

* update default chunk overlap to 10 percent in the database

* default chunk size to 512 at the service layer

* wip

lastFile:backend/src/test/java/com/cloudera/cai/rag/sessions/SessionServiceTest.java

* WIP

lastFile:backend/src/test/java/com/cloudera/cai/rag/projects/ProjectControllerTest.java

* wip on refactoring session creation

lastFile:backend/src/test/java/com/cloudera/cai/rag/sessions/SessionServiceTest.java

* wip

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* WIP

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* mob next [ci-skip] [ci skip] [skip ci]

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* insert new session with data source functioning

* wip

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* remove mcp.json and example file

* wip

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* WIP

lastFile:backend/src/main/java/com/cloudera/cai/rag/datasources/RagDataSourceRepository.java

* wip on session creation

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* wip

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionRepository.java

* WIP add session kb

lastFile:backend/src/main/java/com/cloudera/cai/rag/sessions/SessionService.java

* wip

lastFile:backend/src/main/java/com/cloudera/cai/rag/datasources/RagDataSourceRepository.java

* remove redundant type

* simplify request

* add embedding model and fix default project id

* add associated data source id to the session type

* small refactor to text area

* dynamic columns on the uploaded files table

* drop databases

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* WIP

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* wip

lastFile:ui/src/pages/DataSources/ManageTab/UploadedFilesHeader.tsx

* WIP on session doc dialog

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* drop databases

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* WIP

lastFile:ui/src/pages/RagChatTab/FooterComponents/SessionDocuments.tsx

* use

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* drop databases

lastFile:ui/src/pages/RagChatTab/FooterComponents/ChatSessionDocuments.tsx

* wip on badge for doc uploading status

* WIP

lastFile:ui/src/pages/DataSources/ManageTab/UploadedFilesTable.tsx

* drop databases

lastFile:ui/src/pages/DataSources/ManageTab/UploadedFilesTable.tsx

* WIP on doc icon badging

lastFile:ui/src/pages/RagChatTab/FooterComponents/ChatSessionDocuments.tsx

* WIP

lastFile:ui/src/pages/RagChatTab/FooterComponents/ChatSessionDocuments.tsx

* get all data source Ids including associated

lastFile:ui/src/pages/RagChatTab/FooterComponents/ChatSessionDocuments.tsx

* formatting

* drop databases

lastFile:llm-service/summaries/6/graph_store.json

* start dragndroppin

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* WIP drag and drop

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* remove drop code from input

lastFile:ui/src/pages/RagChatTab/FooterComponents/RagChatQueryInput.tsx

* drop databases

lastFile:ui/src/pages/RagChatTab/RagChat.tsx

* get drag and drop working

* remove unused imports

* invalidate queries to provide status

* small ui improvements to chat doc ui

* add files to chat with no active session

* fix: revert to using chat engine when no tools is selected

* Update release version to dev-testing

* small UI change to swap textarea with dropzone

* refetch suggested questions after file is added in drag and drop

* wip on badge for doc uploading status

* filter data sources count for metrics based on associated session id

* remove old code for completedIndexing

* modify test for metrics

* nits

* remove bad directory

---------

Co-authored-by: jwatson <[email protected]>
Co-authored-by: Baasit Sharief <[email protected]>
Co-authored-by: Michael Liu <[email protected]>
Co-authored-by: actions-user <[email protected]>

1.23.0

08 Jul 18:02
5ad0c04
Compare
Choose a tag to compare
Streaming chat cleanup & in-process docling (#247)

* refactoring/cleanup

* type fixes and import cleanup

* name changes

lastFile:ui/src/pages/RagChatTab/State/RagChatContext.tsx

* wip

lastFile:llm-service/app/services/query/querier.py

* event testing

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* wip event queue

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* moving poison pill around

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* event wip

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* WIP event queue

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* WIP event queue

lastFile:llm-service/app/services/query/chat_events.py

* WIP even queue

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* wip on chat events

lastFile:llm-service/app/routers/index/sessions/__init__.py

* work in progress on chat events

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* WIP event queue

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* drop databases

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* wip on openai streaming events

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* send additional done after we're really done

lastFile:llm-service/app/routers/index/sessions/__init__.py

* getting close to streaming events on non openai agents

lastFile:llm-service/app/services/query/agents/tool_calling_querier.py

* gracefully shutdown handler and close loop

* python cleanup

* error handling in the non-openai streaming

* cleanup

* render contents of a tags and remove chat event queue

* input for date tool

* default input

* fix duplicated timestamp issue

* mypy

* remove openaiagent

* update lock file

* Docling enhancements to parsing support and sampling summary nodes (#248)

* work on docling native parsing

* native parsing to json work, no formatting

* docling + markdown + page numbers

* small cleanup

* use docling for parsing docs

* only use docling readers for pdf and html

* change chunk API to return a list of results

* batch the csv results

* conditionally condense questions

* Revert "batch the csv results"

This reverts commit ff3936fc7c2490609137d070052beab889c7a619.

* Revert "change chunk API to return a list of results"

This reverts commit 4ea267f7ebdf19fb442ace03eed53caf5e922d94.

* implement block-sampling for summarization

* add test for block sampling

* add some prints for debugging

* update test and doc strings

* handle case where no content in summary

* better status code

* fix mypy

---------

Co-authored-by: jwatson <[email protected]>

* Update release version to dev-testing

* filter out non-final agent response

* fixed typos

* fixed typos wip

* put limit on error retries on suggested questions and show error when opening suggested questions

* format agent stream output for non final response

* better error messages

* refactor and check for mistral agent

* fix issue with long responses to session name

* return empty string when no chat history instead of throwing exception

* throw error using bedrock model that does not support tool calling

* error handling for non tool calling models

lastFile:llm-service/app/services/query/querier.py

* mypy fix and refactoring

* use chat when no tools with tool calling enable

* remove print and modify error message

* remove print

---------

Co-authored-by: Baasit Sharief <[email protected]>
Co-authored-by: Elijah Williams <[email protected]>
Co-authored-by: Michael Liu <[email protected]>
Co-authored-by: actions-user <[email protected]>

1.23.0-beta

12 Jun 23:13
ce534dd
Compare
Choose a tag to compare
1.23.0-beta Pre-release
Pre-release
Remove crew, replace with custom tool-calling (#243)

* wip on moving away from crew

* wip

lastFile:llm-service/app/services/query/agents/crewai_querier.py

* drop databases

lastFile:llm-service/app/services/query/agents/crewai_querier.py

* WIP basic tool calling and minor refactoring of retriever tool

lastFile:llm-service/app/services/query/tools/retriever.py

* not working usage of openai agent

* basic streaming example

* wip on openai tool using

* provide summaries to the retrieval tool

* added source nodes to OpenAI agent stream

* minor change to prompt

* wip on supporting bedrock

* WIP streaming for non open ai models

* add conditional for openai

* support for non openai agents and refactor

* minor fix to return types

* remove crew

* minor change to check for empty response

* fix mypy, ruff issues

* Revert "bump mui packages that seemed to address issues with x-charts"

This reverts commit 864b770f611ee0e4d85e44b2b2dedbe34e83e3d7.

* Revert "update hide legend"

This reverts commit b4db0dde75ab3235345fa2452cff4e8d187a00db.

* remove the last crew bits

* added verbosity for non openai agents

* added missing print dashes

* better error handling for bedrock model availability

* fix mypy

* fix writing source nodes

---------

Co-authored-by: Elijah Williams <[email protected]>
Co-authored-by: Michael Liu <[email protected]>
Co-authored-by: Baasit Sharief <[email protected]>

1.22.2

12 Jun 20:05
8332fc4
Compare
Choose a tag to compare
add branch (#242)

hotifx

12 Jun 18:21
8332fc4
Compare
Choose a tag to compare
hotifx Pre-release
Pre-release
add branch (#242)

1.22.1

12 Jun 14:38
eb7ceb4
Compare
Choose a tag to compare
kill the startup script if python fails to start (#237)

* kill the startup script if python fails to start

* Update scripts/startup_app.sh

Co-authored-by: Copilot <[email protected]>

---------

Co-authored-by: Copilot <[email protected]>