fix publishing

.changeset/solid-months-doubt.md

@@ -0,0 +1,5 @@
+---
+"llama-cloud-services": patch
+---
+
+Fix publishing

py/CHANGELOG.md

@@ -1,17 +1,5 @@
 # llama-cloud-services-py
 
-## 0.6.90
-
-### Patch Changes
-
-- 19cbb25: Remove extension filter
-
-## 0.6.89
-
-### Patch Changes
-
-- b9b83c9: Parse bounding boxes from extract jobs results in agent data
-
 ## 0.6.88
 
 ### Patch Changes

py/llama_cloud_services/beta/agent_data/__init__.py

@@ -11,9 +11,6 @@ from .schema import (
     InvalidExtractionData,
     ExtractedFieldMetadata,
     ExtractedFieldMetaDataDict,
-    FieldCitation,
-    BoundingBox,
-    PageDimensions,
 )
 from .client import AsyncAgentDataClient
 
@@ -31,7 +28,4 @@ __all__ = [
     "InvalidExtractionData",
     "ExtractedFieldMetadata",
     "ExtractedFieldMetaDataDict",
-    "FieldCitation",
-    "BoundingBox",
-    "PageDimensions",
 ]

py/llama_cloud_services/beta/agent_data/schema.py

@@ -174,22 +174,6 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
     )
 
 
-class BoundingBox(BaseModel):
-    """Bounding box coordinates for a citation location on a page."""
-
-    x: float = Field(description="X coordinate of the bounding box origin")
-    y: float = Field(description="Y coordinate of the bounding box origin")
-    w: float = Field(description="Width of the bounding box")
-    h: float = Field(description="Height of the bounding box")
-
-
-class PageDimensions(BaseModel):
-    """Dimensions of a page in the source document."""
-
-    width: float = Field(description="Width of the page")
-    height: float = Field(description="Height of the page")
-
-
 class FieldCitation(BaseModel):
     page: Optional[int] = Field(
         None, description="The page number that the field occurred on"
@@ -198,14 +182,6 @@ class FieldCitation(BaseModel):
         None,
         description="The original text this field's value was derived from",
     )
-    bounding_boxes: Optional[List[BoundingBox]] = Field(
-        None,
-        description="Bounding boxes indicating where the citation appears on the page",
-    )
-    page_dimensions: Optional[PageDimensions] = Field(
-        None,
-        description="Dimensions of the page containing the citation",
-    )
 
 
 class ExtractedFieldMetadata(BaseModel):
@@ -225,10 +201,6 @@ class ExtractedFieldMetadata(BaseModel):
         None,
         description="The confidence score for the field based on the extracted text only",
     )
-    parsing_confidence: Optional[float] = Field(
-        None,
-        description="The confidence score for the field based on the parsing/OCR quality",
-    )
     citation: Optional[List[FieldCitation]] = Field(
         None,
         description="The citation for the field, including page number and matching text",

py/llama_cloud_services/parse/base.py

@@ -751,9 +751,11 @@ class LlamaParse(BasePydanticReader):
             file_path = str(file_input)
             file_ext = os.path.splitext(file_path)[1].lower()
             if file_ext not in SUPPORTED_FILE_TYPES:
-                mime_type = "application/octet-stream"
-            else:
-                mime_type = mimetypes.guess_type(file_path)[0]
+                raise Exception(
+                    f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
+                    f"Current file type: {file_ext}"
+                )
+            mime_type = mimetypes.guess_type(file_path)[0]
             # Open the file here for the duration of the async context
             # load data, set the mime type
             fs = fs or get_default_fs()

py/llama_parse/CHANGELOG.md

@@ -1,20 +1,5 @@
 # llama_parse
 
-## 0.6.90
-
-### Patch Changes
-
-- 19cbb25: Remove extension filter
-- Updated dependencies [19cbb25]
-  - llama-cloud-services-py@0.6.90
-
-## 0.6.89
-
-### Patch Changes
-
-- Updated dependencies [b9b83c9]
-  - llama-cloud-services-py@0.6.89
-
 ## 0.6.88
 
 ### Patch Changes

py/llama_parse/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama_parse",
-  "version": "0.6.90",
+  "version": "0.6.88",
   "description": "",
   "main": "index.js",
   "private": false,

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.90"
+version = "0.6.88"
 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>=0.6.90"]
+dependencies = ["llama-cloud-services>=0.6.88"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services-py",
-  "version": "0.6.90",
+  "version": "0.6.88",
   "private": false,
   "license": "MIT",
   "scripts": {},

py/pyproject.toml

@@ -23,7 +23,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.90"
+version = "0.6.88"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/unit_tests/beta/agent/test_agent_data_schema.py

@@ -11,12 +11,10 @@ from llama_cloud.types.aggregate_group import AggregateGroup
 from pydantic import BaseModel, Field, ValidationError
 
 from llama_cloud_services.beta.agent_data.schema import (
-    BoundingBox,
     ExtractedData,
     ExtractedFieldMetadata,
     FieldCitation,
     InvalidExtractionData,
-    PageDimensions,
     TypedAgentData,
     TypedAggregateGroup,
     calculate_overall_confidence,
@@ -665,69 +663,3 @@ def test_field_conflict_in_schema():
     assert isinstance(
         extracted["majority_opinion"]["reasoning"], ExtractedFieldMetadata
     )
-
-
-def test_parse_extracted_field_metadata_with_bounding_boxes():
-    """Test parse_extracted_field_metadata with bounding boxes and page dimensions."""
-    raw_metadata = {
-        "document_type": {
-            "citation": [
-                {
-                    "page": 1,
-                    "matching_text": "FACTURE ORIGINALE",
-                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                }
-            ],
-            "parsing_confidence": 1.0,
-            "extraction_confidence": 0.7252506422636493,
-            "confidence": 0.7252506422636493,
-        },
-        "summary": {
-            "citation": [
-                {
-                    "page": 1,
-                    "matching_text": "FACTURE ORIGINALE",
-                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                },
-                {
-                    "page": 1,
-                    "matching_text": "Café filtre assiette — $1.90",
-                    "bounding_boxes": [
-                        {"x": 10.56, "y": 172.83, "w": 171.85, "h": 497.01}
-                    ],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                },
-            ],
-            "parsing_confidence": 1.0,
-            "extraction_confidence": 0.5700013128334419,
-            "confidence": 0.5700013128334419,
-        },
-    }
-
-    result = parse_extracted_field_metadata(raw_metadata)
-
-    # Verify document_type citation with bounding boxes
-    assert isinstance(result["document_type"], ExtractedFieldMetadata)
-    assert result["document_type"].parsing_confidence == 1.0
-    assert result["document_type"].extraction_confidence == 0.7252506422636493
-    assert result["document_type"].confidence == 0.7252506422636493
-    assert len(result["document_type"].citation) == 1
-
-    citation = result["document_type"].citation[0]
-    assert citation.page == 1
-    assert citation.matching_text == "FACTURE ORIGINALE"
-    assert len(citation.bounding_boxes) == 1
-    assert citation.bounding_boxes[0] == BoundingBox(x=77.28, y=615.12, w=70.6, h=7.2)
-    assert citation.page_dimensions == PageDimensions(width=222.24, height=736.56)
-
-    # Verify summary citation with multiple bounding boxes
-    assert isinstance(result["summary"], ExtractedFieldMetadata)
-    assert len(result["summary"].citation) == 2
-    assert result["summary"].citation[0].bounding_boxes[0].x == 77.28
-    assert result["summary"].citation[1].bounding_boxes[0].x == 10.56
-
-    # Verify round-trip serialization
-    result2 = parse_extracted_field_metadata(result)
-    assert result2 == result

py/uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
     "python_full_version >= '3.14'",
@@ -1609,7 +1609,7 @@ wheels = [
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.88"
+version = "0.6.85"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },

ts/llama_cloud_services/CHANGELOG.md

@@ -1,23 +1,5 @@
 # llama-cloud-services
 
-## 0.5.3
-
-### Patch Changes
-
-- d7864af: bugfixes in retry logic for LlamaExtract and LlamaClassify
-
-## 0.5.2
-
-### Patch Changes
-
-- 997bcc8: Add types for bounding boxes
-
-## 0.5.1
-
-### Patch Changes
-
-- d5b18a0: Fix publishing
-
 ## 0.5.0
 
 ### Minor Changes

ts/llama_cloud_services/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.5.3",
+  "version": "0.5.0",
   "type": "module",
   "license": "MIT",
   "scripts": {

ts/llama_cloud_services/src/beta/agent/index.ts

@@ -2,14 +2,11 @@ export { AgentClient, createAgentDataClient } from "./client";
 
 export type {
   AggregateAgentDataOptions,
-  BoundingBox,
   ComparisonOperator,
   ExtractedData,
   ExtractedFieldMetadata,
   ExtractedFieldMetadataDict,
-  FieldCitation,
   FilterOperation,
-  PageDimensions,
   SearchAgentDataOptions,
   StatusType,
   TypedAgentData,

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

@@ -28,44 +28,6 @@ export type ComparisonOperator =
  */
 export type FilterOperation = RawFilterOperation;
 
-/**
- * Bounding box coordinates for a citation location on a page
- */
-export interface BoundingBox {
-  /** X coordinate of the bounding box origin */
-  x: number;
-  /** Y coordinate of the bounding box origin */
-  y: number;
-  /** Width of the bounding box */
-  w: number;
-  /** Height of the bounding box */
-  h: number;
-}
-
-/**
- * Dimensions of a page in the source document
- */
-export interface PageDimensions {
-  /** Width of the page */
-  width: number;
-  /** Height of the page */
-  height: number;
-}
-
-/**
- * Citation information for an extracted field
- */
-export interface FieldCitation {
-  /** The page number that the field occurred on */
-  page?: number;
-  /** The original text this field's value was derived from */
-  matching_text?: string;
-  /** Bounding boxes indicating where the citation appears on the page */
-  bounding_boxes?: BoundingBox[];
-  /** Dimensions of the page containing the citation */
-  page_dimensions?: PageDimensions;
-}
-
 /**
  * Metadata for an extracted field, including confidence and citation information
  */
@@ -76,11 +38,16 @@ export interface ExtractedFieldMetadata {
   confidence?: number;
   /** The confidence score for the field based on the extracted text only */
   extraction_confidence?: number;
-  /** The confidence score for the field based on the parsing/OCR quality */
-  parsing_confidence?: number;
   citation?: FieldCitation[];
 }
 
+export interface FieldCitation {
+  /** The page number that the field occurred on */
+  page?: 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

ts/llama_cloud_services/src/classify.ts

@@ -108,19 +108,20 @@ async function pollForJobCompletion({
     }
     const response =
       await getClassifyJobApiV1ClassifierJobsClassifyJobIdGet(jobOptions);
+    if (!response.response.ok) {
+      numIterations++;
+    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
-        throw new Error("There was an error extracting data from your file.");
-      } else if (
-        status == StatusEnum.SUCCESS ||
-        status == StatusEnum.PARTIAL_SUCCESS
-      ) {
+        throw new Error("There was an error during the classification job.");
+      } else if (status == StatusEnum.SUCCESS) {
         return true;
+      } else {
+        numIterations++;
+        await sleep(interval * 1000);
       }
     }
-    numIterations++;
-    await sleep(interval * 1000);
   }
 }
 
@@ -168,7 +169,7 @@ async function getJobResult({
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (response.response.ok && typeof response.data != "undefined") {
+    if (typeof response.data != "undefined") {
       return response.data as ClassifyJobResults;
     } else {
       throw new Error(

ts/llama_cloud_services/src/extract.ts

@@ -296,16 +296,20 @@ async function pollForJobCompletion(
       return false;
     }
     const response = await getJobApiV1ExtractionJobsJobIdGet(jobOptions);
+    if (!response.response.ok) {
+      numIterations++;
+    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
         throw new Error("There was an error extracting data from your file.");
       } else if (status == StatusEnum.SUCCESS) {
         return true;
+      } else {
+        numIterations++;
+        await sleep(interval * 1000);
       }
     }
-    numIterations++;
-    await sleep(interval * 1000);
   }
 }
 
@@ -346,7 +350,7 @@ async function getJobResult(
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (response.response.ok && typeof response.data != "undefined") {
+    if (typeof response.data != "undefined") {
       return {
         data: response.data.data,
         extractionMetadata: response.data.extraction_metadata,