Merge branch 'main' of https://github.com/raspawar/llama_index

.github/pull_request_template.md

@@ -29,11 +29,10 @@ Please delete options that are not relevant.
 
 ## How Has This Been Tested?
 
-Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
+Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.
 
-- [ ] Added new unit/integration tests
-- [ ] Added new notebook (that tests end-to-end)
-- [ ] I stared at the code and made sure it makes sense
+- [ ] I added new unit tests to cover this change
+- [ ] I believe this change is already covered by existing unit tests
 
 ## Suggested Checklist:
 

.github/workflows/coverage.yml

@@ -0,0 +1,71 @@
+name: Check Coverage
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+env:
+  POETRY_VERSION: "1.8.3"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest-unit-tester
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9"]
+    steps:
+      - name: clear space
+        env:
+          CI: true
+        shell: bash
+        run: rm -rf /opt/hostedtoolcache/*
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: update rustc
+        run: rustup update stable
+      - name: Install Poetry
+        run: pipx install poetry==${{ env.POETRY_VERSION }}
+      - name: Set up python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+          cache-dependency-path: "**/poetry.lock"
+      - uses: pantsbuild/actions/init-pants@v5-scie-pants
+        with:
+          # v0 makes it easy to bust the cache if needed
+          # just increase the integer to start with a fresh cache
+          gha-cache-key: v1-py${{ matrix.python_version }}
+          named-caches-hash: v1-py${{ matrix.python_version }}
+          pants-python-version: ${{ matrix.python-version }}
+          pants-ci-config: pants.toml
+      - name: Check BUILD files
+        run: |
+          pants tailor --check :: -docs/::
+      - name: Run coverage checks on changed packages
+        run: |
+          # Get the changed files
+          CHANGED_FILES=$(pants list --changed-since=origin/main)
+
+          # Find which roots contain changed files
+          FILTER_PATTERNS="["
+          for file in $CHANGED_FILES; do
+            root=$(echo "$file" | cut -d'/' -f1,2,3)
+            if [[ ! "$FILTER_PATTERNS" =~ "$root" ]]; then
+              FILTER_PATTERNS="${FILTER_PATTERNS}'${root}',"
+            fi
+          done
+
+          # remove the last comma and close the bracket
+          FILTER_PATTERNS="${FILTER_PATTERNS%,}]"
+
+          echo "Coverage filter patterns: $FILTER_PATTERNS"
+
+          pants --level=error --no-local-cache test \
+            --test-use-coverage \
+            --changed-since=origin/main \
+            --coverage-py-filter="$FILTER_PATTERNS"

CHANGELOG.md

@@ -1,5 +1,147 @@
 # ChangeLog
 
+## [2024-10-03]
+
+### `llama-index-core` [0.11.16]
+
+- Treat non-dict tool JSON function arguments as empty (instead of unexpected raise) (#16316)
+- Fixing instrumentation for workflows (#16290)
+- (workaround) Suppress token detaching exception during workflow tracing (#16364)
+- Raise warning instead of error when nodes have no content (#16354)
+- Fix typo in BasePGRetriever causing graph context to not be added (#16357)
+
+### `llama-index-embeddings-vertex-endpoint` [0.1.0]
+
+- adding vertex endpoint embedding (#16351)
+
+### `llama-index-llms-fireworks` [0.2.1]
+
+- Adding support in FireworksAI for Meta 3.2 Models: 1b-instruct; 3b-instruct; 11b-vision; 90b-vision (#16349)
+
+### `llama-index-multi-modal-llms-openai` [0.2.1]
+
+- Refactor OpenAI `update_tool_calls` (#16309)
+
+### `llama-index-vector-stores-milvus` [0.2.7]
+
+- Add support for nested MetadataFilters and FilterOperator.IS_EMPTY (#16329)
+
+## [2024-10-02]
+
+### `llama-index-core` [0.11.15]
+
+- added `to_dict()`, `from_dict()` and serializers for workflow context (#16250)
+- Ability to cancel workflow execution with `handler.cancel_run()` (#16320)
+- (breaking) Refactor `WorkflowHandler.run_step()` so user manually emits Event to start next step in workflow (#16277)
+
+### `llama-index-embeddings-oracleai` [0.1.0]
+
+- Oraclevs integration (#16161)
+
+### `llama-index-experimental` [0.4.0]
+
+- nudge-ft package and add an example for expanding your dataset (#16269)
+
+### `llama-index-llms-anthropic` [0.3.3]
+
+- Add support for prompt caching for Anthropic LLM (#16270)
+
+### `llama-index-llms-gemini` [0.3.6]
+
+- Output token usage in raw data for Google Gemini LLMs (#16313)
+
+### `llama-index-llms-openai` [0.2.10]
+
+- add 4o mini to azure openai models (#16335)
+
+### `llama-index-llms-vertex` [0.3.7]
+
+- Rremoving safety settings from generation config for Vertex AI models (#16337)
+
+### `llama-index-multi-modal-llms-huggingface` [0.1.0]
+
+- LlamaIndex Multi_Modal_Llms Integration: Huggingface (#16133)
+
+### `llama-index-readers-minio` [0.2.1]
+
+- rm extra print statements & replace create tmpfile function (#16291)
+
+### `llama-index-readers-oracleai` [0.1.0]
+
+- Oraclevs integration (#16161)
+
+### `llama-index-readers-web` [0.2.3]
+
+- Add Zyte Web Reader (#16197)
+
+### `llama-index-retrievers-bm25` [0.4.0]
+
+- bump deps for latest bm25s version (#16339)
+- Update BM25 retriever to use metadata (#16267)
+
+### `llama-index-storage-chat-store-redis` [0.3.2]
+
+- fix check for async client in redis chat store (#16321)
+
+### `llama-index-storage-chat-store-upstash` [0.1.0]
+
+- Upstash Storage Chat Store Integration (#16237)
+
+### `llama-index-vector-stores-milvus` [0.2.6]
+
+- milvus: always set self.\_collection (#16306)
+- Fix milvus collection creation with index_config (#16165)
+
+### `llama-index-vector-stores-oracledb` [0.1.0]
+
+- Oracledb integration (#16161)
+
+## `llama-index-vector-stores-postgres` [0.2.6]
+
+- Support TEXT_MATCH FilterOperator in Postgres Vector Store (#16304)
+
+## [2024-09-26]
+
+### `llama-index-core` [0.11.14]
+
+- Enhance insert Method in BaseIndex to Support Customizable Transformations (#16206)
+- Ensure ChatMemoryBuffer's chat history never begins with a TOOL message (#16214)
+- safe prompt helper string formatting (#16219)
+- [Feature Request] Support max concurrent workflow_instance.run() executions (#16215)
+- Workflows + Human In The Loop Dedicated Support (#16220)
+
+### `llama-index-graph-stores-neptune` [0.2.2]
+
+- fix NoneType object error when passing in provided client (#16174)
+
+### `llama-index-llms-ollama` [0.3.3]
+
+- fix ollama chat missing `keep_alive` (#16182)
+
+### `llama-index-llms-vertex` [0.3.6]
+
+- Fix vertex init function (#16216)
+
+### `llama-index-multi-modal-llms-mistral` [0.1.0]
+
+- Add support for Mistral Multi modal LLM (#16191)
+
+### `llama-index-readers-jira` [0.3.0]
+
+- Add pagination support for Jira Reader (#16226)
+
+### `llama-index-vector-stores-azurecosmosmongo` [0.2.1]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.1.0]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-deeplake` [0.2.1]
+
+- Add missing JWT dependency (#16236)
+
 ## [2024-09-24]
 
 ### `llama-index-core` [0.11.13]

Makefile

@@ -11,7 +11,7 @@ lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
 	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
 
 test:	## Run tests via pants
-	pants --level=error --no-local-cache --changed-since=origin/main --changed-dependents=transitive test
+	pants --level=error --no-local-cache --changed-since=origin/main --changed-dependents=transitive --no-test-use-coverage test
 
 test-core:	## Run tests via pants
 	pants --no-local-cache test llama-index-core/::

docs/docs/CHANGELOG.md

@@ -1,5 +1,147 @@
 # ChangeLog
 
+## [2024-10-03]
+
+### `llama-index-core` [0.11.16]
+
+- Treat non-dict tool JSON function arguments as empty (instead of unexpected raise) (#16316)
+- Fixing instrumentation for workflows (#16290)
+- (workaround) Suppress token detaching exception during workflow tracing (#16364)
+- Raise warning instead of error when nodes have no content (#16354)
+- Fix typo in BasePGRetriever causing graph context to not be added (#16357)
+
+### `llama-index-embeddings-vertex-endpoint` [0.1.0]
+
+- adding vertex endpoint embedding (#16351)
+
+### `llama-index-llms-fireworks` [0.2.1]
+
+- Adding support in FireworksAI for Meta 3.2 Models: 1b-instruct; 3b-instruct; 11b-vision; 90b-vision (#16349)
+
+### `llama-index-multi-modal-llms-openai` [0.2.1]
+
+- Refactor OpenAI `update_tool_calls` (#16309)
+
+### `llama-index-vector-stores-milvus` [0.2.7]
+
+- Add support for nested MetadataFilters and FilterOperator.IS_EMPTY (#16329)
+
+## [2024-10-02]
+
+### `llama-index-core` [0.11.15]
+
+- added `to_dict()`, `from_dict()` and serializers for workflow context (#16250)
+- Ability to cancel workflow execution with `handler.cancel_run()` (#16320)
+- (breaking) Refactor `WorkflowHandler.run_step()` so user manually emits Event to start next step in workflow (#16277)
+
+### `llama-index-embeddings-oracleai` [0.1.0]
+
+- Oraclevs integration (#16161)
+
+### `llama-index-experimental` [0.4.0]
+
+- nudge-ft package and add an example for expanding your dataset (#16269)
+
+### `llama-index-llms-anthropic` [0.3.3]
+
+- Add support for prompt caching for Anthropic LLM (#16270)
+
+### `llama-index-llms-gemini` [0.3.6]
+
+- Output token usage in raw data for Google Gemini LLMs (#16313)
+
+### `llama-index-llms-openai` [0.2.10]
+
+- add 4o mini to azure openai models (#16335)
+
+### `llama-index-llms-vertex` [0.3.7]
+
+- Rremoving safety settings from generation config for Vertex AI models (#16337)
+
+### `llama-index-multi-modal-llms-huggingface` [0.1.0]
+
+- LlamaIndex Multi_Modal_Llms Integration: Huggingface (#16133)
+
+### `llama-index-readers-minio` [0.2.1]
+
+- rm extra print statements & replace create tmpfile function (#16291)
+
+### `llama-index-readers-oracleai` [0.1.0]
+
+- Oraclevs integration (#16161)
+
+### `llama-index-readers-web` [0.2.3]
+
+- Add Zyte Web Reader (#16197)
+
+### `llama-index-retrievers-bm25` [0.4.0]
+
+- bump deps for latest bm25s version (#16339)
+- Update BM25 retriever to use metadata (#16267)
+
+### `llama-index-storage-chat-store-redis` [0.3.2]
+
+- fix check for async client in redis chat store (#16321)
+
+### `llama-index-storage-chat-store-upstash` [0.1.0]
+
+- Upstash Storage Chat Store Integration (#16237)
+
+### `llama-index-vector-stores-milvus` [0.2.6]
+
+- milvus: always set self.\_collection (#16306)
+- Fix milvus collection creation with index_config (#16165)
+
+### `llama-index-vector-stores-oracledb` [0.1.0]
+
+- Oracledb integration (#16161)
+
+## `llama-index-vector-stores-postgres` [0.2.6]
+
+- Support TEXT_MATCH FilterOperator in Postgres Vector Store (#16304)
+
+## [2024-09-26]
+
+### `llama-index-core` [0.11.14]
+
+- Enhance insert Method in BaseIndex to Support Customizable Transformations (#16206)
+- Ensure ChatMemoryBuffer's chat history never begins with a TOOL message (#16214)
+- safe prompt helper string formatting (#16219)
+- [Feature Request] Support max concurrent workflow_instance.run() executions (#16215)
+- Workflows + Human In The Loop Dedicated Support (#16220)
+
+### `llama-index-graph-stores-neptune` [0.2.2]
+
+- fix NoneType object error when passing in provided client (#16174)
+
+### `llama-index-llms-ollama` [0.3.3]
+
+- fix ollama chat missing `keep_alive` (#16182)
+
+### `llama-index-llms-vertex` [0.3.6]
+
+- Fix vertex init function (#16216)
+
+### `llama-index-multi-modal-llms-mistral` [0.1.0]
+
+- Add support for Mistral Multi modal LLM (#16191)
+
+### `llama-index-readers-jira` [0.3.0]
+
+- Add pagination support for Jira Reader (#16226)
+
+### `llama-index-vector-stores-azurecosmosmongo` [0.2.1]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-azurecosmosnosql` [1.1.0]
+
+- Azure Cosmos DB Filtered Vector Search (#16175)
+
+### `llama-index-vector-stores-deeplake` [0.2.1]
+
+- Add missing JWT dependency (#16236)
+
 ## [2024-09-24]
 
 ### `llama-index-core` [0.11.13]

docs/docs/api_reference/embeddings/oracleai.md

@@ -0,0 +1,4 @@
+::: llama_index.embeddings.oracleai
+    options:
+      members:
+        - OracleEmbeddings