Upstream changes for v2.2.0 release (#35)

* Upstream changes for 2.2.0 release

Signed-off-by: Shubhadeep Das <[email protected]>

Author: shubhadeepd

.gitignore

@@ -1,13 +1,16 @@
 # Python Exclusions
 .venv
 **__pycache__**
+src/nvidia_rag.egg-info/
+dist/*
 
 # Helm Exclusions
 **/helm-charts/*.tgz
 
 # Docker Compose exclusions
 deploy/compose/volumes
 uploaded_files/
+**tmp-data**
 
 # Visual Studio Code
 .vscode
@@ -19,4 +22,60 @@ uploaded_files/
 docs/_*
 
 # Notebook checkpoints
-notebooks/.ipynb_checkpoints
+**.ipynb_checkpoints**
+
+# Ignore generated or temporary files managed by the Workbench
+.project/*
+!.project/spec.yaml
+!.project/configpacks
+
+# General ignores
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Temp directories, notebooks created by jupyterlab
+.ipynb_checkpoints
+.Trash-*/
+.jupyter/
+.local/
+
+# Python distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Workbench Project Layout

.project/configpacks

@@ -0,0 +1,10 @@
+*defaults.ContainerUser
+*bash.PreBuild
+*defaults.EnvVars
+*defaults.Readme
+*defaults.Entrypoint
+*apt.PackageManager
+*bash.PreLanguage
+*python.PipPackageManager
+*bash.PostBuild
+*jupyterlab.JupyterLab

.project/spec.yaml

@@ -0,0 +1,91 @@
+specVersion: v2
+specMinorVersion: 2
+meta:
+    name: rag
+    image: project-rag
+    description: ""
+    labels: []
+    createdOn: "2024-12-06T19:19:11Z"
+    defaultBranch: main
+layout: []
+environment:
+    base:
+        registry: nvcr.io
+        image: nvidia/ai-workbench/python-basic:1.0.2
+        build_timestamp: "20241001182612"
+        name: Python Basic
+        supported_architectures: []
+        cuda_version: ""
+        description: A Python Base with Jupyterlab
+        entrypoint_script: ""
+        labels:
+            - ubuntu
+            - python3
+            - jupyterlab
+        apps:
+            - name: jupyterlab
+              type: jupyterlab
+              class: webapp
+              start_command: jupyter lab --allow-root --port 8888 --ip 0.0.0.0 --no-browser --NotebookApp.base_url=\$PROXY_PREFIX --NotebookApp.default_url=/lab --NotebookApp.allow_origin='*'
+              health_check_command: '[ \$(echo url=\$(jupyter lab list | head -n 2 | tail -n 1 | cut -f1 -d'' '' | grep -v ''Currently'' | sed "s@/?@/lab?@g") | curl -o /dev/null -s -w ''%{http_code}'' --config -) == ''200'' ]'
+              stop_command: jupyter lab stop 8888
+              user_msg: ""
+              logfile_path: ""
+              timeout_seconds: 60
+              icon_url: ""
+              webapp_options:
+                autolaunch: true
+                port: "8888"
+                proxy:
+                    trim_prefix: false
+                url_command: jupyter lab list | head -n 2 | tail -n 1 | cut -f1 -d' ' | grep -v 'Currently'
+        programming_languages:
+            - python3
+        icon_url: https://workbench.download.nvidia.com/static/img/ai-workbench-icon-rectangle.jpg
+        image_version: 1.0.5
+        os: linux
+        os_distro: ubuntu
+        os_distro_release: "22.04"
+        schema_version: v2
+        user_info:
+            uid: ""
+            gid: ""
+            username: ""
+        package_managers:
+            - name: apt
+              binary_path: /usr/bin/apt
+              installed_packages:
+                - curl
+                - git
+                - git-lfs
+                - python3
+                - gcc
+                - python3-dev
+                - python3-pip
+                - vim
+            - name: pip
+              binary_path: /usr/bin/pip
+              installed_packages:
+                - jupyterlab==4.2.4
+        package_manager_environment:
+            name: ""
+            target: ""
+    compose_file_path: deploy/workbench/compose.yaml
+execution:
+    apps: []
+    resources:
+        gpu:
+            requested: 0
+        sharedMemoryMB: 0
+    secrets:
+        - variable: NGC_API_KEY
+          description: NVIDIA API Key (starts with "nvapi-")
+    mounts:
+        - type: project
+          target: /project/
+          description: Project directory
+          options: rw
+        - type: volume
+          target: /nvwb-shared-volume/
+          description: ""
+          options: volumeName=nvwb-shared-volume

.python-version

@@ -0,0 +1 @@
+3.12

CHANGELOG.md

@@ -3,6 +3,47 @@ All notable changes to this project will be documented in this file.
 The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
 
 
+## [2.2.0] - 2025-07-08
+
+This release adds B200 platform support, a native Python API, and major enhancements for multimodal and metadata features. It also improves deployment flexibility and customization across the RAG blueprint.
+
+### Added
+- Support deploying the blueprint on B200 platform.
+- Support for [native python API](./docs/python-client.md)
+  - Refactoring code and directory to support python API
+  - Better modularization for easier customization
+  - Moved to `uv` as the package manager for this project
+- Added support for configurable vector store consistency levels (Bounded/Strong/Session) to optimize retrieval performance vs accuracy trade-offs.
+- [Capability to add custom metadata](./docs/custom-metadata.md) for files and metadata based filtering
+- Documentation of [using Multi Instance GPUs](./docs/mig-deployment.md). Reduces minimum GPU requirement for helm charts to 3xH100.
+- [Multi collection based retrieval](./docs/multi-collection-retrieval.md) support
+- [Audio files (.mp3 and .wav) support](./docs/audio_ingestion.md)
+- Support of using [Vision Language Model](./docs/vlm.md) based generation for charts and images
+- Support for [generating summaries](./docs/summarization.md) of uploaded files
+- Sample user interface enhancements
+  - Support for non-blocking file upload
+  - More efficient error reporting for ingestion failures
+- [Prompt customization](./docs/prompt-customization.md) support without rebuilding images
+- Added support to enable infographics, which improves accuracy for documents containing text in image format.
+  - See [this guide](./docs/accuracy_perf.md#ingestion-and-chunking) for details
+- New customizations
+  - How to support non nvingest based ingestion + retrieval
+  - How to enable [CPU based milvus](./docs/milvus-configuration.md)
+  - How to enable [nemoretriever-parse](./docs/nemoretriever-parse-extraction.md) as an alternate PDF parser
+  - How to use [standalone nv-ingest python client](./docs/nv-ingest-standalone.md) to do ingestion
+- [Nvidia AI Workbench support](./deploy/workbench/)
+
+### Changed
+- [Changed API schema](./docs/api_reference/) to support newly added features
+  - POST /collections to be deprecated in favour of POST /collection for ingestor-server
+  - New endpoint GET /summary added for rag-server
+  - Metadata information available as part of GET /collections and GET /documents API
+  - Check out [migration guide](./docs/migration_guide.md#migration-guide-rag-v210-to-rag-v220) for detailed changes at API level
+- [Optimized batch mode](./docs/accuracy_perf.md#ingestion-batch-mode-optimization) ingestion support to improve perf for multi user concurrent file upload.
+
+### Known Issues
+Check out [this section](./docs/troubleshooting.md#known-issues) to understand the known issues present for this release.
+
 ## [2.1.0] - 2025-05-13
 
 This release reduces overall GPU requirement for the deployment of the blueprint. It also improves the performance and stability for both docker and helm based deployments.