fix: skip examples for codespell

.github/workflows/build_package_py.yml

@@ -6,11 +6,8 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "py/**"
   pull_request:
-    paths:
-      - "py/**"
+
 env:
   UV_VERSION: "0.7.20"
 

.github/workflows/build_package_ts.yml

@@ -1,13 +1,5 @@
 name: Build Package - TypeScript
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - "ts/**"
-  pull_request:
-    paths:
-      - "ts/**"
+on: [pull_request]
 
 jobs:
   pre_release:

.github/workflows/lint_ts.yml

@@ -4,11 +4,9 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "ts/**"
   pull_request:
-    paths:
-      - "ts/**"
+    branches:
+      - main
 
 env:
   TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}

.github/workflows/test_e2e_py.yml

@@ -1,38 +0,0 @@
-name: Test end-to-end - Python
-
-on:
-  pull_request:
-    paths:
-      - "py/**"
-
-env:
-  UV_VERSION: "0.7.20"
-  LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
-
-jobs:
-  test_e2e:
-    runs-on: ubuntu-latest
-    strategy:
-      # You can use PyPy versions in python-version.
-      # For example, pypy-2.7 and pypy-3.8
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-        with:
-          version: ${{ env.UV_VERSION }}
-
-      - name: Set up Python
-        run: uv python install ${{ matrix.python-version }} && uv python pin ${{ matrix.python-version }}
-
-      - name: Run Tests
-        working-directory: py
-        run: uv run pytest unit_tests/ tests/ -v
-
-      - name: Remove virtual environment
-        working-directory: py
-        run: rm -rf .venv/

.github/workflows/test_py.yml

@@ -4,14 +4,11 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "py/**"
   pull_request:
-    paths:
-      - "py/**"
 
 env:
   UV_VERSION: "0.7.20"
+  LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
 
 jobs:
   test:
@@ -35,7 +32,7 @@ jobs:
 
       - name: Run Tests
         working-directory: py
-        run: uv run pytest unit_tests/ -v
+        run: uv run -- pytest tests/**/test_*.py
 
       - name: Remove virtual environment
         working-directory: py

.github/workflows/test_ts.yml

@@ -4,11 +4,9 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "ts/**"
   pull_request:
-    paths:
-      - "ts/**"
+    branches:
+      - main
 
 env:
   TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
@@ -17,8 +15,7 @@ env:
   LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
 
 jobs:
-  test:
-    name: Test - TypeScript
+  lint:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -34,4 +31,4 @@ jobs:
         run: pnpm install --no-frozen-lockfile
       - name: Run tests
         working-directory: ts/llama_cloud_services/
-        run: pnpm test
+        run: pnpm test --run

.pre-commit-config.yaml

@@ -33,7 +33,7 @@ repos:
     rev: v1.0.1
     hooks:
       - id: mypy
-        exclude: ^py/tests|^py/unit_tests
+        exclude: ^py/tests/
         additional_dependencies:
           [
             "types-requests",
@@ -63,13 +63,13 @@ repos:
     rev: v3.0.3
     hooks:
       - id: prettier
-        exclude: ^(uv.lock|ts/llama_cloud_services/pnpm-lock.yaml)
+        exclude: uv.lock
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.6
     hooks:
       - id: codespell
         additional_dependencies: [tomli]
-        exclude: ^(uv.lock|docs|ts|examples)
+        exclude: ^(uv.lock|examples|ts)
         args:
           [
             "--ignore-words-list",

examples/parse/parsing_modes/demo_layout_agent_mode_visual_citations.ipynb

@@ -147,7 +147,7 @@
     "documents = []\n",
     "\n",
     "for i, page in enumerate(pages):\n",
-    "    # loop through items of the page\n",
+    "    # loop trough items of the page\n",
     "    for item in page[\"items\"]:\n",
     "        document = Document(\n",
     "            text=item[\"md\"], extra_info={\"bbox\": item[\"bBox\"], \"page\": i}\n",

extract.md

@@ -208,5 +208,5 @@ Another option (orthogonal to the above) is to break the document into smaller s
 
 ## Additional Resources
 
-- [Example Notebook](docs/examples-py/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
+- [Example Notebook](examples/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
 - [Discord Community](https://discord.com/invite/eN6D2HQ4aX) - Get help and share feedback

parse.md

@@ -97,7 +97,7 @@ for page in result.pages:
     print(page.structuredData)
 ```
 
-See more details about the result object in the [example notebook](./docs/examples-py/parse/demo_json_tour.ipynb).
+See more details about the result object in the [example notebook](./examples/parse/demo_json_tour.ipynb).
 
 ### Using with file object / bytes
 
@@ -153,10 +153,10 @@ Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex D
 
 Several end-to-end indexing examples can be found in the examples folder
 
-- [Getting Started](docs/examples-py/parse/demo_basic.ipynb)
-- [Advanced RAG Example](docs/examples-py/parse/demo_advanced.ipynb)
-- [Raw API Usage](docs/examples-py/parse/demo_api.ipynb)
-- [Result Object Tour](docs/examples-py/parse/demo_json_tour.ipynb)
+- [Getting Started](./examples/parse/demo_basic.ipynb)
+- [Advanced RAG Example](./examples/parse/demo_advanced.ipynb)
+- [Raw API Usage](./examples/parse/demo_api.ipynb)
+- [Result Object Tour](./examples/parse/demo_json_tour.ipynb)
 
 ## Documentation
 

py/llama_cloud_services/beta/agent_data/schema.py

@@ -181,15 +181,11 @@ class ExtractedFieldMetadata(BaseModel):
     Metadata for an extracted data field, such as confidence, and citation information.
     """
 
-    reasoning: Optional[str] = Field(
-        None,
-        description="symbol for how the citation/confidence was derived: 'INFERRED FROM TEXT', 'VERBATIM EXTRACTION'",
-    )
     confidence: Optional[float] = Field(
         None,
         description="The confidence score for the field, combined with parsing confidence if applicable",
     )
-    extraction_confidence: Optional[float] = Field(
+    extracted_confidence: Optional[float] = Field(
         None,
         description="The confidence score for the field based on the extracted text only",
     )
@@ -210,66 +206,42 @@ ExtractedFieldMetaDataDict = Dict[
 def parse_extracted_field_metadata(
     field_metadata: dict[str, Any],
 ) -> ExtractedFieldMetaDataDict:
-    return {
-        k: _parse_extracted_field_metadata_recursive(v)
-        for k, v in field_metadata.items()
-        if k not in _METADATA_FIELDS_SIBLING_TO_LEAF
-    }
-
-
-_METADATA_FIELDS_SIBLING_TO_LEAF = {"reasoning"}
-
-
-def _parse_extracted_field_metadata_recursive(
-    field_value: Any,
-    additional_fields: dict[str, Any] = {},
-) -> Union[ExtractedFieldMetadata, Dict[str, Any], list[Any]]:
     """
     Parse the extracted field metadata into a dictionary of field names to field metadata.
     """
+    result: ExtractedFieldMetaDataDict = {}
+    for field_name, field_value in field_metadata.items():
+        if isinstance(field_value, ExtractedFieldMetadata):
+            # support running this multiple times
+            result[field_name] = field_value
+        elif isinstance(field_value, dict):
+            if "confidence" in field_value or "citations" in field_value:
+                try:
+                    validated = ExtractedFieldMetadata.model_validate(field_value)
 
-    if isinstance(field_value, ExtractedFieldMetadata):
-        # support running this multiple times
-        return field_value
-    elif isinstance(field_value, dict):
-        # reasoning explicitly excluded, as it is included next to subfields, for example
-        # "dimensions.width" is a leaf, but there will still potentially be a "dimensions.reasoning"
-        indicator_fields = {"confidence", "extraction_confidence", "citation"}
-        if len(indicator_fields.intersection(field_value.keys())) > 0:
-            try:
-                merged = {**field_value, **additional_fields}
-                validated = ExtractedFieldMetadata.model_validate(merged)
-
-                # grab the citation from the array. This is just an array for backwards compatibility.
-                if "citation" in field_value and len(field_value["citation"]) > 0:
-                    first_citation = field_value["citation"][0]
-                    if "page" in first_citation and isinstance(
-                        first_citation["page"], numbers.Number
-                    ):
-                        validated.page_number = int(first_citation["page"])  # type: ignore
-                    if "matching_text" in first_citation and isinstance(
-                        first_citation["matching_text"], str
-                    ):
-                        validated.matching_text = first_citation["matching_text"]
-                return validated
-            except ValidationError:
-                pass
-        additional_fields = {
-            k: v
-            for k, v in field_value.items()
-            if k in _METADATA_FIELDS_SIBLING_TO_LEAF
-        }
-        return {
-            k: _parse_extracted_field_metadata_recursive(v, additional_fields)
-            for k, v in field_value.items()
-            if k not in _METADATA_FIELDS_SIBLING_TO_LEAF
-        }
-    elif isinstance(field_value, list):
-        return [_parse_extracted_field_metadata_recursive(item) for item in field_value]
-    else:
-        raise ValueError(
-            f"Invalid field value: {field_value}. Expected ExtractedFieldMetadata, dict, or list"
-        )
+                    # grab the citation from the array. This is just an array for backwards compatibility.
+                    if "citations" in field_value and len(field_value["citations"]) > 0:
+                        first_citation = field_value["citations"][0]
+                        if "page_number" in first_citation and isinstance(
+                            first_citation["page_number"], numbers.Number
+                        ):
+                            validated.page_number = int(first_citation["page_number"])  # type: ignore
+                        if "matching_text" in first_citation and isinstance(
+                            first_citation["matching_text"], str
+                        ):
+                            validated.matching_text = first_citation["matching_text"]
+                    result[field_name] = validated
+                    continue
+                except ValidationError:
+                    pass
+            result[field_name] = parse_extracted_field_metadata(field_value)
+        elif isinstance(field_value, list):
+            result[field_name] = [
+                parse_extracted_field_metadata(item) for item in field_value
+            ]
+        else:
+            result[field_name] = field_value
+    return result
 
 
 class ExtractedData(BaseModel, Generic[ExtractedT]):

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.54"
+version = "0.6.53"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"
 readme = "README.md"
 license = "MIT"
-dependencies = ["llama-cloud-services>=0.6.54"]
+dependencies = ["llama-cloud-services>=0.6.53"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/pyproject.toml

@@ -17,7 +17,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.54"
+version = "0.6.53"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/tests/beta/agent_data/test_agent_data_schema.py

@@ -230,20 +230,20 @@ def test_parse_extracted_field_metadata():
     raw_metadata = {
         "name": {
             "confidence": 0.95,
-            "citation": [{"page": 1, "matching_text": "John Smith"}],
+            "citations": [{"page_number": 1, "matching_text": "John Smith"}],
         },
         "age": {
             "confidence": 0.87,
-            "citation": [
+            "citations": [
                 {
-                    "page": 2.0,  # Float page number
+                    "page_number": 2.0,  # Float page number
                     "matching_text": "25 years old",
                 }
             ],
         },
         "email": {
             "confidence": 0.92,
-            "citation": [],  # Empty citations
+            "citations": [],  # Empty citations
         },
     }
 
@@ -268,110 +268,6 @@ def test_parse_extracted_field_metadata():
     assert result["email"].confidence == 0.92
 
 
-def test_parse_extracted_field_metadata_complex():
-    """Test parse_extracted_field_metadata with new citation format and reasoning field."""
-    raw_metadata = {
-        "title": {
-            "reasoning": "Combined key parametrics and construction from the datasheet for a structured title.",
-            "citation": [
-                {
-                    "page": 1,
-                    "matching_text": "PHE844/F844, Film, Metallized Polypropylene, Safety, 0.47 uF",
-                }
-            ],
-            "extraction_confidence": 0.9470628580889779,
-            "confidence": 0.9470628580889779,
-        },
-        "manufacturer": {
-            "reasoning": "VERBATIM EXTRACTION",
-            "citation": [{"page": 1, "matching_text": "YAGEO KEMET"}],
-            "extraction_confidence": 0.9997446550976602,
-            "confidence": 0.9997446550976602,
-        },
-        "features": [
-            {
-                "reasoning": "VERBATIM EXTRACTION",
-                "citation": [
-                    {"page": 1, "matching_text": "Features</td><td>EMI Safety"}
-                ],
-                "extraction_confidence": 0.9999308195540074,
-                "confidence": 0.9999308195540074,
-            },
-            {
-                "reasoning": "VERBATIM EXTRACTION",
-                "citation": [
-                    {"page": 1, "matching_text": "THB Performance</td><td>Yes"}
-                ],
-                "extraction_confidence": 0.8642493886452225,
-                "confidence": 0.8642493886452225,
-            },
-        ],
-        "dimensions": {
-            "length": {
-                "citation": [{"page": 1, "matching_text": "L</td><td>41mm MAX"}],
-                "extraction_confidence": 0.8986941382802304,
-                "confidence": 0.8986941382802304,
-            },
-            "width": {
-                "citation": [{"page": 1, "matching_text": "T</td><td>13mm MAX"}],
-                "extraction_confidence": 0.9999377974447091,
-                "confidence": 0.9999377974447091,
-            },
-            "reasoning": "VERBATIM EXTRACTION",
-        },
-    }
-
-    result = parse_extracted_field_metadata(raw_metadata)
-    assert result == {
-        "title": ExtractedFieldMetadata(
-            reasoning="Combined key parametrics and construction from the datasheet for a structured title.",
-            confidence=0.9470628580889779,
-            extraction_confidence=0.9470628580889779,
-            page_number=1,
-            matching_text="PHE844/F844, Film, Metallized Polypropylene, Safety, 0.47 uF",
-        ),
-        "manufacturer": ExtractedFieldMetadata(
-            reasoning="VERBATIM EXTRACTION",
-            confidence=0.9997446550976602,
-            extraction_confidence=0.9997446550976602,
-            page_number=1,
-            matching_text="YAGEO KEMET",
-        ),
-        "features": [
-            ExtractedFieldMetadata(
-                reasoning="VERBATIM EXTRACTION",
-                confidence=0.9999308195540074,
-                extraction_confidence=0.9999308195540074,
-                page_number=1,
-                matching_text="Features</td><td>EMI Safety",
-            ),
-            ExtractedFieldMetadata(
-                reasoning="VERBATIM EXTRACTION",
-                confidence=0.8642493886452225,
-                extraction_confidence=0.8642493886452225,
-                page_number=1,
-                matching_text="THB Performance</td><td>Yes",
-            ),
-        ],
-        "dimensions": {
-            "length": ExtractedFieldMetadata(
-                reasoning="VERBATIM EXTRACTION",
-                confidence=0.8986941382802304,
-                extraction_confidence=0.8986941382802304,
-                page_number=1,
-                matching_text="L</td><td>41mm MAX",
-            ),
-            "width": ExtractedFieldMetadata(
-                reasoning="VERBATIM EXTRACTION",
-                confidence=0.9999377974447091,
-                extraction_confidence=0.9999377974447091,
-                page_number=1,
-                matching_text="T</td><td>13mm MAX",
-            ),
-        },
-    }
-
-
 def create_file(
     id: str = "file-456",
     name: str = "resume.pdf",
@@ -394,12 +290,12 @@ def create_extract_run(
     extraction_metadata: Dict[str, Any] = {
         "name": {
             "confidence": 0.95,
-            "citation": [{"page": 1, "matching_text": "John Doe"}],
+            "citations": [{"page_number": 1, "matching_text": "John Doe"}],
         },
         "age": {"confidence": 0.87},
         "email": {
             "confidence": 0.92,
-            "citation": [{"page": 1, "matching_text": "john@example.com"}],
+            "citations": [{"page_number": 1, "matching_text": "john@example.com"}],
         },
     },
     data_schema: Dict[str, Any] = {},

py/tests/extract/test_benchmark.py

@@ -124,8 +124,8 @@ def extraction_agent(test_case: TestCase, extractor: LlamaExtract):
 
 
 @pytest.mark.skipif(
-    "CI" in os.environ or not LLAMA_CLOUD_API_KEY,
-    reason="LLAMA_CLOUD_API_KEY not set or CI environment not suitable for benchmarking",
+    "CI" in os.environ,
+    reason="CI environment is not suitable for benchmarking",
 )
 @pytest.mark.parametrize("test_case", get_test_cases(), ids=lambda x: x.name)
 @pytest.mark.asyncio(loop_scope="session")

py/tests/index/test_index.py

@@ -16,6 +16,7 @@ from llama_cloud import (
 from llama_cloud.client import LlamaCloud
 from llama_index.core.bridge.pydantic import BaseModel
 from llama_index.core.constants import DEFAULT_BASE_URL
+from llama_index.core.indices.managed.base import BaseManagedIndex
 from llama_index.core.schema import Document, ImageNode
 from llama_cloud_services.index import (
     LlamaCloudIndex,
@@ -27,8 +28,6 @@ api_key = os.environ.get("LLAMA_CLOUD_API_KEY", None)
 organization_id = os.environ.get("LLAMA_CLOUD_ORGANIZATION_ID", None)
 project_name = os.environ.get("LLAMA_CLOUD_PROJECT_NAME", "framework_integration_test")
 
-print("api-key", api_key, "base-url", base_url)
-
 
 @pytest.fixture()
 def remote_file() -> Tuple[str, str]:
@@ -92,6 +91,16 @@ def _setup_index_with_file(
     return pipeline
 
 
+def test_class():
+    names_of_base_classes = [b.__name__ for b in LlamaCloudIndex.__mro__]
+    assert BaseManagedIndex.__name__ in names_of_base_classes
+
+
+def test_conflicting_index_identifiers():
+    with pytest.raises(ValueError):
+        LlamaCloudIndex(name="test", pipeline_id="test", index_id="test")
+
+
 @pytest.mark.skipif(
     not base_url or not api_key, reason="No platform base url or api key set"
 )
@@ -353,9 +362,6 @@ async def test_page_figure_retrieval(index_name: str, local_figures_file: str):
     not base_url or not api_key, reason="No platform base url or api key set"
 )
 @pytest.mark.asyncio
-@pytest.mark.skip(
-    reason="Consistently failing with 'Server disconnected without sending a response'"
-)
 async def test_composite_retriever(index_name: str):
     """Test the LlamaCloudCompositeRetriever with multiple indices."""
     # Create first index with documents

py/unit_tests/index/test_unit_index.py

@@ -1,16 +0,0 @@
-import pytest
-
-from llama_index.core.indices.managed.base import BaseManagedIndex
-from llama_cloud_services.index import (
-    LlamaCloudIndex,
-)
-
-
-def test_class():
-    names_of_base_classes = [b.__name__ for b in LlamaCloudIndex.__mro__]
-    assert BaseManagedIndex.__name__ in names_of_base_classes
-
-
-def test_conflicting_index_identifiers():
-    with pytest.raises(ValueError):
-        LlamaCloudIndex(name="test", pipeline_id="test", index_id="test")

py/uv.lock

@@ -734,7 +734,7 @@ name = "exceptiongroup"
 version = "1.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0b/9f/a65090624ecf468cdca03533906e7c69ed7588582240cfe7cc9e770b50eb/exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88", size = 29749, upload-time = "2025-05-10T17:42:51.123Z" }
 wheels = [
@@ -1587,7 +1587,7 @@ wheels = [
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.54"
+version = "0.6.53"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },

scripts/version-bump.py

@@ -13,26 +13,17 @@ from pathlib import Path
 def get_current_versions() -> tuple[str, str, str]:
     """Get current versions from both pyproject.toml files."""
     # Read main pyproject.toml
-    main_content = Path("py/pyproject.toml").read_text()
+    main_content = Path("pyproject.toml").read_text()
     main_doc = tomlkit.parse(main_content)
-    main_version = main_doc["project"]["version"]
+    main_version = main_doc["tool"]["poetry"]["version"]
 
     # Read llama_parse/pyproject.toml
-    llama_parse_content = Path("py/llama_parse/pyproject.toml").read_text()
+    llama_parse_content = Path("llama_parse/pyproject.toml").read_text()
     llama_parse_doc = tomlkit.parse(llama_parse_content)
-    llama_parse_version = llama_parse_doc["project"]["version"]
-    # Find llama-cloud-services dependency in the dependencies list
-    dependency_version = None
-    for dep in llama_parse_doc["project"]["dependencies"]:
-        if isinstance(dep, str) and dep.startswith("llama-cloud-services"):
-            dependency_version = (
-                dep.split("==")[1]
-                if "==" in dep
-                else dep.split(">=")[1]
-                if ">=" in dep
-                else None
-            )
-            break
+    llama_parse_version = llama_parse_doc["tool"]["poetry"]["version"]
+    dependency_version = llama_parse_doc["tool"]["poetry"]["dependencies"][
+        "llama-cloud-services"
+    ]
 
     return str(main_version), str(llama_parse_version), str(dependency_version)
 
@@ -62,22 +53,19 @@ def validate_versions(
 def set_version(version: str) -> None:
     """Set version across all pyproject.toml files using tomlkit to preserve formatting."""
     # Update main pyproject.toml
-    main_content = Path("py/pyproject.toml").read_text()
+    main_content = Path("pyproject.toml").read_text()
     main_doc = tomlkit.parse(main_content)
-    main_doc["project"]["version"] = version
-    Path("py/pyproject.toml").write_text(tomlkit.dumps(main_doc))
+    main_doc["tool"]["poetry"]["version"] = version
+    Path("pyproject.toml").write_text(tomlkit.dumps(main_doc))
 
     # Update llama_parse/pyproject.toml
-    llama_parse_content = Path("py/llama_parse/pyproject.toml").read_text()
+    llama_parse_content = Path("llama_parse/pyproject.toml").read_text()
     llama_parse_doc = tomlkit.parse(llama_parse_content)
-    llama_parse_doc["project"]["version"] = version
-    for dep_index, dep in enumerate(llama_parse_doc["project"]["dependencies"]):
-        if isinstance(dep, str) and dep.startswith("llama-cloud-services"):
-            llama_parse_doc["project"]["dependencies"][
-                dep_index
-            ] = f"llama-cloud-services>={version}"
-            break
-    Path("py/llama_parse/pyproject.toml").write_text(tomlkit.dumps(llama_parse_doc))
+    llama_parse_doc["tool"]["poetry"]["version"] = version
+    llama_parse_doc["tool"]["poetry"]["dependencies"][
+        "llama-cloud-services"
+    ] = f">={version}"
+    Path("llama_parse/pyproject.toml").write_text(tomlkit.dumps(llama_parse_doc))
 
     click.echo(f"Updated all versions to {version}")
 
@@ -90,7 +78,7 @@ def get_current_branch() -> str:
     return result.stdout.strip()
 
 
-def create_if_not_exists(version: str) -> None:
+def create_and_push_tag(version: str) -> None:
     """Create a git tag and push it."""
     current_branch = get_current_branch()
     if current_branch != "main":
@@ -100,26 +88,12 @@ def create_if_not_exists(version: str) -> None:
         sys.exit(1)
 
     tag_name = f"v{version}"
-    if not tag_exists(version):
-        # Create tag
-        subprocess.run(["git", "tag", tag_name], check=True)
-        click.echo(f"Created tag {tag_name}")
-    else:
-        click.echo(f"Tag {tag_name} already exists")
 
+    # Create tag
+    subprocess.run(["git", "tag", tag_name], check=True)
+    click.echo(f"Created tag {tag_name}")
 
-def tag_exists(version: str) -> bool:
-    """Check if a git tag exists."""
-    tag_name = f"v{version}"
-    result = subprocess.run(
-        ["git", "tag", "-l", tag_name], capture_output=True, text=True, check=True
-    )
-    return tag_name in result.stdout.strip()
-
-
-def push_tag(version: str) -> None:
-    """Push a git tag."""
-    tag_name = f"v{version}"
+    # Push tag
     subprocess.run(["git", "push", "origin", tag_name], check=True)
     click.echo(f"Pushed tag {tag_name}")
 
@@ -160,20 +134,13 @@ def set(version: str) -> None:
 @click.option(
     "--version", help="Version to tag (uses current version if not specified)"
 )
-@click.option(
-    "--push",
-    is_flag=True,
-    help="Push the tag to the remote repository",
-)
-def tag(version: str | None = None, push: bool = False) -> None:
+def tag(version: str | None = None) -> None:
     """Create and push a git tag for the current version."""
     if not version:
         main_version, _, _ = get_current_versions()
         version = main_version
 
-    create_if_not_exists(version)
-    if push:
-        push_tag(version)
+    create_and_push_tag(version)
 
 
 if __name__ == "__main__":

ts/llama_cloud_services/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.2.0",
+  "version": "0.1.0",
   "type": "module",
   "license": "MIT",
   "scripts": {
@@ -9,7 +9,7 @@
     "dev": "bunchee --watch",
     "lint": "eslint src/ --ignore-pattern client/*.ts --no-warn-ignored",
     "format": "prettier --write ./src/",
-    "test": "vitest run --testTimeout=60000",
+    "test": "vitest",
     "test:watch": "vitest --watch",
     "test:ui": "vitest --ui",
     "test:coverage": "vitest --coverage"
@@ -89,12 +89,12 @@
     "@eslint/js": "^9.32.0",
     "@hey-api/client-fetch": "^0.10.1",
     "@hey-api/openapi-ts": "^0.67.5",
-    "@llamaindex/core": "^0.6.19",
+    "@llama-flow/core": "^0.4.1",
+    "@llamaindex/core": "^0.6.18",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^0.4.1",
-    "@types/node": "^20.19.9",
     "@typescript-eslint/eslint-plugin": "^8.38.0",
     "@typescript-eslint/parser": "^8.38.0",
+    "@types/node": "^20.0.0",
     "@vitest/coverage-v8": "^2.0.0",
     "@vitest/ui": "^2.0.0",
     "bunchee": "^6.5.4",
@@ -107,12 +107,12 @@
     "vitest": "^2.0.0"
   },
   "peerDependencies": {
-    "@llamaindex/core": "^0.6.19",
+    "@llama-flow/core": "^0.4.1",
+    "@llamaindex/core": "^0.6.18",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^0.4.1"
+    "llamaindex": "^0.11.23"
   },
   "dependencies": {
-    "ajv": "^8.17.1",
     "p-retry": "^6.2.1",
     "zod": "^3.25.76"
   },

ts/llama_cloud_services/src/LlamaCloudIndex.ts

@@ -1,10 +1,8 @@
 import type { BaseNodePostprocessor } from "@llamaindex/core/postprocessor";
-import {
-  RetrieverQueryEngine,
-  type BaseQueryEngine,
-} from "@llamaindex/core/query-engine";
+import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
 import type { BaseSynthesizer } from "@llamaindex/core/response-synthesizers";
 import type { Document } from "@llamaindex/core/schema";
+import { RetrieverQueryEngine } from "llamaindex/engines";
 import type { CloudRetrieveParams } from "./LlamaCloudRetriever.js";
 import { LlamaCloudRetriever } from "./LlamaCloudRetriever.js";
 import type { CloudConstructorParams } from "./type.js";
@@ -27,14 +25,9 @@ import {
 } from "./api";
 import type { BaseRetriever } from "@llamaindex/core/retriever";
 import { getEnv } from "@llamaindex/env";
-import { createQueryEngineTool, type QueryToolParams } from "./query-tool.js";
-import type { BaseTool } from "@llamaindex/core/llms";
-
-type QueryEngineParams = {
-  responseSynthesizer?: BaseSynthesizer;
-  preFilters?: unknown;
-  nodePostprocessors?: BaseNodePostprocessor[];
-} & CloudRetrieveParams;
+import type { QueryToolParams } from "llamaindex/indices";
+import { Settings } from "llamaindex";
+import { QueryEngineTool } from "llamaindex/tools";
 
 export class LlamaCloudIndex {
   params: CloudConstructorParams;
@@ -45,7 +38,7 @@ export class LlamaCloudIndex {
   }
 
   private async waitForPipelineIngestion(
-    verbose = false,
+    verbose = Settings.debug,
     raiseOnError = false,
   ): Promise<void> {
     const pipelineId = await this.getPipelineId();
@@ -90,7 +83,7 @@ export class LlamaCloudIndex {
 
   private async waitForDocumentIngestion(
     docIds: string[],
-    verbose = false,
+    verbose = Settings.debug,
     raiseOnError = false,
   ): Promise<void> {
     const pipelineId = await this.getPipelineId();
@@ -263,7 +256,13 @@ export class LlamaCloudIndex {
     return new LlamaCloudRetriever({ ...this.params, ...params });
   }
 
-  asQueryEngine(params?: QueryEngineParams): BaseQueryEngine {
+  asQueryEngine(
+    params?: {
+      responseSynthesizer?: BaseSynthesizer;
+      preFilters?: unknown;
+      nodePostprocessors?: BaseNodePostprocessor[];
+    } & CloudRetrieveParams,
+  ): BaseQueryEngine {
     const retriever = new LlamaCloudRetriever({
       ...this.params,
       ...params,
@@ -275,15 +274,19 @@ export class LlamaCloudIndex {
     );
   }
 
-  asQueryTool(params: QueryEngineParams & QueryToolParams): BaseTool {
-    return createQueryEngineTool({
+  asQueryTool(params: QueryToolParams): QueryEngineTool {
+    if (params.options) {
+      params.retriever = this.asRetriever(params.options);
+    }
+
+    return new QueryEngineTool({
       queryEngine: this.asQueryEngine(params),
       metadata: params?.metadata,
       includeSourceNodes: params?.includeSourceNodes ?? false,
     });
   }
 
-  queryTool(params: QueryEngineParams & QueryToolParams) {
+  queryTool(params: QueryToolParams): QueryEngineTool {
     return this.asQueryTool(params);
   }
 

ts/llama_cloud_services/src/beta/agent/client.ts

@@ -261,7 +261,8 @@ export class AgentClient<T = unknown> {
   }
 }
 
-export interface AgentDataClientOptions {
+// eslint-disable-next-line  @typescript-eslint/no-unused-vars
+export interface AgentDataClientOptions<T = unknown> {
   /** API key for the client */
   apiKey?: string;
   /** Base URL for the client */

ts/llama_cloud_services/src/beta/agent/types.ts

@@ -28,31 +28,6 @@ export type ComparisonOperator =
  */
 export type FilterOperation = RawFilterOperation;
 
-/**
- * Metadata for an extracted field, including confidence and citation information
- */
-export interface ExtractedFieldMetadata {
-  /** The reasoning for the confidence score */
-  reasoning?: string;
-  /** The confidence score for the field, combined with parsing confidence if applicable */
-  confidence?: number;
-  /** The confidence score for the field based on the extracted text only */
-  extraction_confidence?: number;
-  /** The page number that the field occurred on */
-  page_number?: number;
-  /** The original text this field's value was derived from */
-  matching_text?: string;
-}
-
-/**
- * Dictionary mapping field names to their metadata
- * Values can be ExtractedFieldMetadata objects, nested dictionaries, or arrays
- */
-export type ExtractedFieldMetadataDict = Record<
-  string,
-  ExtractedFieldMetadata | Record<string, unknown> | unknown[]
->;
-
 /**
  * Base extracted data interface
  */
@@ -60,13 +35,11 @@ export interface ExtractedData<T = unknown> {
   /** The original data that was extracted from the document. For tracking changes. Should not be updated. */
   original_data: T;
   /** The latest state of the data. Will differ if data has been updated. */
-  data: T;
+  data?: T;
   /** The status of the extracted data. Prefer to use the StatusType values, but any string is allowed. */
   status: StatusType | string;
-  /** The overall confidence score for the extracted data. */
-  overall_confidence?: number;
-  /** Page links, and perhaps eventually bounding boxes, for individual fields in the extracted data. */
-  field_metadata?: ExtractedFieldMetadataDict;
+  /** Confidence scores, if any, for each primitive field in the original_data data. */
+  confidence?: Record<string, unknown>;
   /** The ID of the file that was used to extract the data. */
   file_id?: string;
   /** The name of the file that was used to extract the data. */

ts/llama_cloud_services/src/events.ts

@@ -1,5 +1,5 @@
-import { workflowEvent } from "@llamaindex/workflow-core";
-import { zodEvent } from "@llamaindex/workflow-core/util/zod";
+import { workflowEvent } from "@llama-flow/core";
+import { zodEvent } from "@llama-flow/core/util/zod";
 import { z } from "zod";
 import { parseFormSchema } from "./schema";
 

ts/llama_cloud_services/src/parse.ts

@@ -1,11 +1,8 @@
 import { createClient, createConfig } from "@hey-api/client-fetch";
-import {
-  createWorkflow,
-  type InferWorkflowEventData,
-} from "@llamaindex/workflow-core";
-import { createStatefulMiddleware } from "@llamaindex/workflow-core/middleware/state";
-import { withTraceEvents } from "@llamaindex/workflow-core/middleware/trace-events";
-import { pRetryHandler } from "@llamaindex/workflow-core/util/p-retry";
+import { createWorkflow, type InferWorkflowEventData } from "@llama-flow/core";
+import { createStatefulMiddleware } from "@llama-flow/core/middleware/state";
+import { withTraceEvents } from "@llama-flow/core/middleware/trace-events";
+import { pRetryHandler } from "@llama-flow/core/util/p-retry";
 import { fs, getEnv, path } from "@llamaindex/env";
 import {
   type BodyUploadFileApiV1ParsingUploadPost,

ts/llama_cloud_services/src/query-tool.ts

@@ -1,39 +0,0 @@
-import type { JSONValue } from "@llamaindex/core/global";
-import type { ToolMetadata } from "@llamaindex/core/llms";
-import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
-import { tool } from "@llamaindex/core/tools";
-import { z } from "zod";
-
-const DEFAULT_NAME = "llama_cloud_index_tool";
-const DEFAULT_DESCRIPTION =
-  "Useful for retrieving relevant information from document stored in a LlamaCloud Index";
-
-export type QueryToolParams = {
-  metadata?: Omit<ToolMetadata, "parameters"> | undefined;
-  includeSourceNodes?: boolean;
-};
-
-export function createQueryEngineTool(
-  options: { queryEngine: BaseQueryEngine } & QueryToolParams,
-) {
-  const { queryEngine, metadata, includeSourceNodes } = options;
-  return tool({
-    name: metadata?.name ?? DEFAULT_NAME,
-    description: metadata?.description ?? DEFAULT_DESCRIPTION,
-    parameters: z.object({
-      query: z.string({
-        description: "The query to search for",
-      }),
-    }),
-    execute: async ({ query }) => {
-      const response = await queryEngine.query({ query });
-      if (!includeSourceNodes) {
-        return { content: response.message.content } as unknown as JSONValue;
-      }
-      return {
-        content: response.message.content,
-        sourceNodes: response.sourceNodes,
-      } as unknown as JSONValue;
-    },
-  });
-}

ts/llama_cloud_services/tests/integration.test.ts

@@ -350,25 +350,6 @@ describe("Integration Tests", () => {
       }
     });
 
-    it.skipIf(skipIfNoApiKey)("should create query engine tool", async () => {
-      try {
-        const queryEngineTool = index.asQueryTool({
-          metadata: {
-            name: "test-tool",
-            description: "Test tool description",
-          },
-        });
-        expect(queryEngineTool).toBeDefined();
-        expect(typeof queryEngineTool.call).toBe("function");
-        expect(queryEngineTool.metadata.name).toBe("test-tool");
-        expect(queryEngineTool.metadata.description).toBe(
-          "Test tool description",
-        );
-      } catch (error) {
-        console.warn("Query engine tool creation test failed:", error.message);
-      }
-    });
-
     it.skipIf(skipIfNoApiKey)(
       "should get pipeline and project IDs",
       async () => {

ts/llama_cloud_services/tsconfig.json

@@ -14,9 +14,10 @@
     "rootDir": "./src",
     "outDir": "./dist/type",
     "tsBuildInfoFile": "./dist/.tsbuildinfo",
+    "emitDeclarationOnly": true,
     "incremental": true,
     "lib": ["ES2022", "DOM", "DOM.Iterable", "DOM.AsyncIterable"],
-    "types": ["node"]
+    "types": []
   },
   "include": ["./src"],
   "exclude": ["node_modules"]