alita-sdk 0.3.318__tar.gz → 0.3.320__tar.gz

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.318
+Version: 0.3.320
 Summary: SDK for building langchain agents using resources from Alita
 Author-email: Artem Rozumenko <artyom.rozumenko@gmail.com>, Mikalai Biazruchka <mikalai_biazruchka@epam.com>, Roman Mitusov <roman_mitusov@epam.com>, Ivan Krakhmaliuk <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/runtime/langchain/document_loaders/AlitaExcelLoader.py

@@ -17,6 +17,7 @@ import pandas as pd
 from json import loads
 
 from langchain_core.tools import ToolException
+from langchain_core.documents import Document
 from .AlitaTableLoader import AlitaTableLoader
     
 
@@ -65,6 +66,20 @@ class AlitaExcelLoader(AlitaTableLoader):
         else:
             return df.to_string(index=False)
 
+    def load(self) -> list:
+        docs = []
+        content_per_sheet = self.get_content()
+        for sheet_name, content in content_per_sheet.items():
+            metadata = {
+                "source": f'{self.file_path}:{sheet_name}',
+                "sheet_name": sheet_name,
+                "file_type": "excel",
+                "excel_by_sheets": self.excel_by_sheets,
+                "return_type": self.return_type,
+            }
+            docs.append(Document(page_content=f"Sheet: {sheet_name}\n {str(content)}", metadata=metadata))
+        return docs
+
     def read(self, lazy: bool = False):
         df = pd.read_excel(self.file_path, sheet_name=None)
         docs = []

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/runtime/langchain/document_loaders/AlitaTableLoader.py

@@ -17,8 +17,6 @@ from langchain_core.documents import Document
 from typing import List, Optional, Iterator
 from json import dumps
 from .utils import cleanse_data
-from ..tools.log import print_log
-
 
 class AlitaTableLoader(BaseLoader):
     def __init__(self,
@@ -74,7 +72,6 @@ class AlitaTableLoader(BaseLoader):
                 docs.append(Document(page_content=row, metadata=metadata))
                 continue
             if self.json_documents:
-                # print_log(row)
                 metadata['columns'] = list(row.keys())
                 metadata['og_data'] = dumps(row)
                 docs.append(Document(page_content=self.row_processor(row), metadata=metadata))

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/runtime/langchain/document_loaders/constants.py

@@ -122,6 +122,7 @@ loaders_map = {
         'class': AlitaExcelLoader,
         'is_multimodal_processing': False,
         'kwargs': {
+            'excel_by_sheets': True,
             'raw_content': True,
             'cleanse': False
         },
@@ -131,6 +132,7 @@ loaders_map = {
         'class': AlitaExcelLoader,
         'is_multimodal_processing': False,
         'kwargs': {
+            'excel_by_sheets': True,
             'raw_content': True,
             'cleanse': False
         },

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/ado/test_plan/test_plan_wrapper.py

@@ -411,11 +411,11 @@ class TestPlanApiWrapper(NonCodeIndexerToolkit):
     def _index_tool_params(self):
         """Return the parameters for indexing data."""
         return {
+            'chunking_tool': (Literal['html', ''], Field(description="Name of chunking tool", default='html')),
             "plan_id": (int, Field(description="ID of the test plan for which test cases are requested")),
             "suite_ids": (Optional[List[int]], Field(description='List of test suite IDs for which test cases are requested '
                                                                  '(can be empty for all suites indexing from the plan). '
                                                                  'Example: [2, 23]', default=[])),
-            'chunking_tool':(Literal['html', ''], Field(description="Name of chunking tool", default='html'))
         }
 
     @extend_with_parent_available_tools

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/ado/wiki/ado_wrapper.py

@@ -248,9 +248,9 @@ class AzureDevOpsApiWrapper(NonCodeIndexerToolkit):
     def _index_tool_params(self):
         """Return the parameters for indexing data."""
         return {
+            'chunking_tool': (Literal['markdown', ''], Field(description="Name of chunking tool", default='markdown')),
             "wiki_identifier": (str, Field(description="Wiki identifier to index, e.g., 'ABCProject.wiki'")),
             'title_contains': (Optional[str], Field(default=None, description="Optional filter to include only pages with titles containing exact this string")),
-            'chunking_tool':(Literal['markdown', ''], Field(description="Name of chunking tool", default='markdown'))
         }
 
     @extend_with_parent_available_tools

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/base_indexer_toolkit.py

@@ -87,10 +87,10 @@ BaseStepbackSearchParams = create_model(
 BaseIndexDataParams = create_model(
     "indexData",
     __base__=BaseIndexParams,
-    progress_step=(Optional[int], Field(default=10, ge=0, le=100,
-                         description="Optional step size for progress reporting during indexing")),
     clean_index=(Optional[bool], Field(default=False,
                        description="Optional flag to enforce clean existing index before indexing new data")),
+    progress_step=(Optional[int], Field(default=10, ge=0, le=100,
+                         description="Optional step size for progress reporting during indexing")),
     chunking_config=(Optional[dict], Field(description="Chunking tool configuration", default_factory=dict)),
 )
 

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/confluence/api_wrapper.py

@@ -1656,8 +1656,7 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
 
     @extend_with_parent_available_tools
     def get_available_tools(self):
-        # Confluence-specific tools
-        confluence_tools = [
+        return [
             {
                 "name": "create_page",
                 "ref": self.create_page,
@@ -1772,9 +1771,4 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
                 "description": self.get_page_attachments.__doc__,
                 "args_schema": GetPageAttachmentsInput,
             }
-        ]
-
-        # Add standardized vector search tools from base class
-        vector_search_tools = self._get_vector_search_tools()
-
-        return confluence_tools + vector_search_tools
+        ]

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/elitea_base.py

@@ -39,10 +39,13 @@ BaseIndexParams = create_model(
 BaseCodeIndexParams = create_model(
     "BaseCodeIndexParams",
     collection_suffix=(str, Field(description="Suffix for collection name (max 7 characters) used to separate datasets", min_length=1, max_length=7)),
+    clean_index=(Optional[bool], Field(default=False, description="Optional flag to enforce clean existing index before indexing new data")),
+    progress_step=(Optional[int], Field(default=5, ge=0, le=100,
+                         description="Optional step size for progress reporting during indexing")),
     branch=(Optional[str], Field(description="Branch to index files from. Defaults to active branch if None.", default=None)),
     whitelist=(Optional[List[str]], Field(description='File extensions or paths to include. Defaults to all files if None. Example: ["*.md", "*.java"]', default=None)),
     blacklist=(Optional[List[str]], Field(description='File extensions or paths to exclude. Defaults to no exclusions if None. Example: ["*.md", "*.java"]', default=None)),
-    clean_index=(Optional[bool], Field(default=False, description="Optional flag to enforce clean existing index before indexing new data")),
+
 )
 
 RemoveIndexParams = create_model(
@@ -115,10 +118,10 @@ BaseStepbackSearchParams = create_model(
 BaseIndexDataParams = create_model(
     "indexData",
     __base__=BaseIndexParams,
-    progress_step=(Optional[int], Field(default=5, ge=0, le=100,
-                         description="Optional step size for progress reporting during indexing")),
     clean_index=(Optional[bool], Field(default=False,
                        description="Optional flag to enforce clean existing index before indexing new data")),
+    progress_step=(Optional[int], Field(default=5, ge=0, le=100,
+                         description="Optional step size for progress reporting during indexing")),
     chunking_tool=(Literal[None,'markdown', 'statistical', 'proposal'], Field(description="Name of chunking tool", default=None)),
     chunking_config=(Optional[dict], Field(description="Chunking tool configuration", default_factory=dict)),
 )

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/figma/api_wrapper.py

@@ -320,6 +320,10 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
             )
         ]
 
+        if not node_ids:
+            yield from ()
+            return
+
         images = self._client.get_file_images(file_key, node_ids).images or {}
         total_images = len(images)
         if total_images == 0:

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/utils/content_parser.py

@@ -207,7 +207,7 @@ def process_document_by_type(content, extension_source: str, document: Document
     try:
         chunks = process_content_by_type(content, extension_source, llm, chunking_config)
     except Exception as e:
-        msg = f"Error during content for file {extension_source}:\n{e}"
+        msg = f"Error during content parsing for file {extension_source}:\n{e}"
         logger.warning(msg)
         yield Document(
             page_content=msg,
@@ -218,7 +218,7 @@ def process_document_by_type(content, extension_source: str, document: Document
         yield Document(
             page_content=sanitize_for_postgres(chunk.page_content),
             metadata={**document.metadata, **chunk.metadata}
-                )
+        )
 
 
 def process_content_by_type(content, filename: str, llm=None, chunking_config=None) -> \
@@ -233,7 +233,7 @@ def process_content_by_type(content, filename: str, llm=None, chunking_config=No
             if content is None:
                 logger.warning(
                     f"'{IndexerKeywords.CONTENT_IN_BYTES.value}' ie expected but not found in document metadata.")
-                return
+                return []
 
             temp_file.write(content)
             temp_file.flush()
@@ -241,7 +241,7 @@ def process_content_by_type(content, filename: str, llm=None, chunking_config=No
             loader_config = loaders_map.get(extension)
             if not loader_config:
                 logger.warning(f"No loader found for file extension: {extension}. File: {temp_file_path}")
-                return
+                return []
 
             loader_cls = loader_config['class']
             loader_kwargs = loader_config['kwargs']

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/xray/api_wrapper.py

@@ -561,6 +561,8 @@ class XrayApiWrapper(NonCodeIndexerToolkit):
 
     def _index_tool_params(self, **kwargs) -> dict[str, tuple[type, Field]]:
         return {
+            'chunking_tool': (Literal['json', ''],
+                              Field(description="Name of chunking tool for base document", default='json')),
             'jql': (Optional[str], Field(description="""JQL query for searching test cases in Xray.
 
             Standard JQL query syntax for filtering Xray test cases. Examples:
@@ -595,8 +597,6 @@ class XrayApiWrapper(NonCodeIndexerToolkit):
             'skip_attachment_extensions': (Optional[List[str]], Field(
                 description="List of file extensions to skip when processing attachments (e.g., ['.exe', '.zip', '.bin'])",
                 default=None)),
-            'chunking_tool': (Literal['json', ''],
-                              Field(description="Name of chunking tool for base document", default='json')),
         }
 
     def _get_tests_direct(self, jql: str) -> List[Dict]:

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/zephyr_enterprise/api_wrapper.py

@@ -155,8 +155,9 @@ class ZephyrApiWrapper(NonCodeIndexerToolkit):
         Returns a list of fields for index_data args schema.
         """
         return {
-            "zql": (str, Field(description=zql_description, examples=["folder=\"TestToolkit\"", "name~\"TestToolkit5\""])),
-            'chunking_tool': (Literal['json', ''], Field(description="Name of chunking tool", default='json'))
+            'chunking_tool': (Literal['json', ''], Field(description="Name of chunking tool", default='json')),
+            "zql": (str, Field(description=zql_description, examples=["folder=\"TestToolkit\"", "name~\"TestToolkit5\""]))
+
         }
 
     def _base_loader(self, zql: str, **kwargs) -> Generator[Document, None, None]:

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk/tools/zephyr_scale/api_wrapper.py

@@ -1198,6 +1198,7 @@ class ZephyrScaleApiWrapper(NonCodeIndexerToolkit):
         Returns a list of fields for index_data args schema.
         """
         return {
+            "chunking_tool": (Literal['json', ''], Field(description="Name of chunking tool", default='json')),
             "project_key": (str, Field(description="Jira project key filter")),
             "jql":(str, Field(description="""JQL-like query for searching test cases.
             Supported fields:
@@ -1216,7 +1217,6 @@ class ZephyrScaleApiWrapper(NonCodeIndexerToolkit):
             Example:
                 'folder = "Authentication" AND label in ("Smoke", "Critical") AND text ~ "login" AND orderBy = "name" AND orderDirection = "ASC"'
             """)),
-            'chunking_tool': (Literal['json', ''], Field(description="Name of chunking tool", default='json'))
         }
 
     def _base_loader(self, project_key: str, jql: str, **kwargs) -> Generator[Document, None, None]:

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.318
+Version: 0.3.320
 Summary: SDK for building langchain agents using resources from Alita
 Author-email: Artem Rozumenko <artyom.rozumenko@gmail.com>, Mikalai Biazruchka <mikalai_biazruchka@epam.com>, Roman Mitusov <roman_mitusov@epam.com>, Ivan Krakhmaliuk <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.318 → alita_sdk-0.3.320}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.318"
+version = "0.3.320"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"