alita-sdk 0.3.344__tar.gz → 0.3.345__tar.gz

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.344
+Version: 0.3.345
 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
@@ -82,7 +82,7 @@ Requires-Dist: gitpython==3.1.43; extra == "tools"
 Requires-Dist: atlassian-python-api~=4.0.7; extra == "tools"
 Requires-Dist: jira==3.8.0; extra == "tools"
 Requires-Dist: qtest-swagger-client==0.0.3; extra == "tools"
-Requires-Dist: testrail-api==1.13.2; extra == "tools"
+Requires-Dist: testrail-api==1.13.4; extra == "tools"
 Requires-Dist: azure-devops==7.1.0b4; extra == "tools"
 Requires-Dist: msrest==0.7.1; extra == "tools"
 Requires-Dist: python-graphql-client~=0.4.3; extra == "tools"

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk/runtime/langchain/document_loaders/AlitaPowerPointLoader.py

@@ -36,15 +36,23 @@ class AlitaPowerPointLoader:
     def read_pptx_slide(self, slide, index):
         text_content = f'Slide: {index}\n'
         for shape in slide.shapes:
-            if hasattr(shape, "text"):
-                text_content += shape.text + "\n"
+            if hasattr(shape, "text_frame") and shape.text_frame is not None:
+                for paragraph in shape.text_frame.paragraphs:
+                    for run in paragraph.runs:
+                        if run.hyperlink and run.hyperlink.address:
+                            link_text = run.text.strip() or "Link"
+                            link_url = run.hyperlink.address
+                            text_content += f" [{link_text}]({link_url}) "
+                        else:
+                            text_content += run.text
+                text_content += "\n"
             elif self.extract_images and shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
                 try:
                     caption = perform_llm_prediction_for_image_bytes(shape.image.blob, self.llm)
                 except:
                     caption = "unknown"
                 text_content += "\n**Image Transcript:**\n" + caption + "\n--------------------\n"
-        return text_content
+        return text_content + "\n"
 
     def load(self):
         if not self.file_path:

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk/tools/figma/api_wrapper.py

@@ -227,9 +227,9 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
             self._log_tool_event(f"Loading files: {file_keys_include}")
             for file_key in file_keys_include:
                 self._log_tool_event(f"Loading file `{file_key}`")
-                file = self._client.get_file(file_key)
+                file = self._client.get_file(file_key, geometry='depth=1') # fetch only top-level structure (only pages without inner components)
                 if not file:
-                    raise ToolException(f"Unexpected error while retrieving file {file_key}. Probably file is under editing. Try again later.")
+                    raise ToolException(f"Unexpected error while retrieving file {file_key}. Please try specifying the node-id of an inner page.")
                 metadata = {
                     'id': file_key,
                     'file_key': file_key,
@@ -284,20 +284,47 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
             for child in node['children']:
                 texts.extend(self.get_texts_recursive(child))
         return texts
+    
+    def _load_pages(self, document: Document):
+        file_key = document.metadata.get('id', '')
+        node_ids_include = document.metadata.pop('figma_pages_include', [])
+        node_ids_exclude = document.metadata.pop('figma_pages_exclude', [])
+        self._log_tool_event(f"Included pages: {node_ids_include}. Excluded pages: {node_ids_exclude}.")
+        if node_ids_include:
+            # try to fetch only specified pages/nodes in one request
+            file = self._get_file_nodes(file_key,','.join(node_ids_include)) # attempt to fetch only specified pages/nodes in one request
+            if file:
+                return [node['document'] for node in file.get('nodes', {}).values() if 'document' in node]
+        else:
+            # 
+            file = self._client.get_file(file_key)
+            if file:
+                figma_pages = file.document.get('children', [])
+                return [node for node in figma_pages if ('id' in node and node['id'].replace(':', '-') not in node_ids_exclude)]
+        # fallback to loading all pages and filtering them one by one
+        file = self._client.get_file(file_key, geometry='depth=1')
+        if not file:
+            raise ToolException(
+                f"Unexpected error while retrieving file {file_key}. Please try specifying the node-id of an inner page.")
+        figma_pages_raw = file.document.get('children', [])
+        # extract pages one by one
+        if node_ids_include:
+            return [self._get_file_nodes(file_key, node_id) for node_id in node_ids_include]
+        else:
+            # return [self._get_file_nodes(file_key, page["id"]) for page in figma_pages_raw if ('id' in page and page['id'].replace(':', '-') not in node_ids_exclude)]
+            result = []
+            for page in figma_pages_raw:
+                if 'id' in page and page['id'].replace(':', '-') not in node_ids_exclude:
+                    page_res = self._get_file_nodes(file_key, page["id"]).get('nodes', {}).get(page["id"], {}).get("document", {})
+                    result.append(page_res)
+            return result
 
     def _process_document(self, document: Document) -> Generator[Document, None, None]:
         file_key = document.metadata.get('id', '')
         self._log_tool_event(f"Loading details (images) for `{file_key}`")
-        figma_pages = self._client.get_file(file_key).document.get('children', [])
-        node_ids_include = document.metadata.pop('figma_pages_include', [])
-        node_ids_exclude = document.metadata.pop('figma_pages_exclude', [])
+        figma_pages = self._load_pages(document)
         node_types_include = [t.strip().lower() for t in document.metadata.pop('figma_nodes_include', [])]
         node_types_exclude = [t.strip().lower() for t in document.metadata.pop('figma_nodes_exclude', [])]
-        self._log_tool_event(f"Included pages: {node_ids_include}. Excluded pages: {node_ids_exclude}.")
-        if node_ids_include:
-            figma_pages = [node for node in figma_pages if ('id' in node and node['id'].replace(':', '-') in node_ids_include)]
-        elif node_ids_exclude:
-            figma_pages = [node for node in figma_pages if ('id' in node and node['id'].replace(':', '-') not in node_ids_exclude)]
 
         image_nodes = []
         text_nodes = {}
@@ -609,6 +636,12 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
             f"files/{file_key}/nodes?ids={str(ids)}", method="get"
         )
 
+    def _get_file_nodes(self, file_key: str, ids: str, **kwargs):
+        """Reads a specified file nodes by field key from Figma."""
+        return self._client.api_request(
+            f"files/{file_key}/nodes?ids={str(ids)}", method="get"
+        )
+
     @process_output
     def get_file(
         self,

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk/tools/github/github_client.py

@@ -87,7 +87,6 @@ class GitHubClient(BaseModel):
 
     # Using optional variables with None defaults instead of PrivateAttr
     github_api: Optional[Github] = Field(default=None, exclude=True)
-    github_repo_instance: Optional[Repository.Repository] = Field(default=None, exclude=True)
 
     # Adding auth config and repo config as optional fields for initialization
     auth_config: Optional[GitHubAuthConfig] = Field(default=None, exclude=True)
@@ -96,6 +95,19 @@ class GitHubClient(BaseModel):
     # Alita instance
     alita: Optional[Any] = Field(default=None, exclude=True)
 
+    @property
+    def github_repo_instance(self) -> Optional[Repository.Repository]:
+        if not hasattr(self, "_github_repo_instance") or self._github_repo_instance is None:
+            try:
+                if self.github_api and self.github_repository:
+                    self._github_repo_instance = self.github_api.get_repo(self.github_repository)
+                else:
+                    self._github_repo_instance = None
+            except Exception as e:
+                # Only raise when accessed, not during initialization
+                return ToolException(e)
+        return self._github_repo_instance
+
     @model_validator(mode='before')
     def initialize_github_client(cls, values):
         """
@@ -144,15 +156,6 @@ class GitHubClient(BaseModel):
             else:
                 values["github_api"] = Github(base_url=values["github_base_url"], auth=auth)
 
-            # Get repository instance
-            if values.get("github_repository"):
-                values["github_repo_instance"] = values["github_api"].get_repo(values["github_repository"])
-        else:
-            # Initialize with default authentication if no auth_config provided
-            values["github_api"] = Github(base_url=values.get("github_base_url", DEFAULT_BASE_URL))
-            if values.get("github_repository"):
-                values["github_repo_instance"] = values["github_api"].get_repo(values["github_repository"])
-
         return values
 
     @staticmethod

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk/tools/testrail/api_wrapper.py

@@ -10,7 +10,7 @@ from pydantic import SecretStr, create_model, model_validator
 from pydantic.fields import Field, PrivateAttr
 from testrail_api import StatusCodeError, TestRailAPI
 
-from ..chunkers.code.constants import get_file_extension
+from ..chunkers.code.constants import get_file_extension, image_extensions
 from ..non_code_indexer_toolkit import NonCodeIndexerToolkit
 from ..utils.available_tools_decorator import extend_with_parent_available_tools
 from ...runtime.utils.utils import IndexerKeywords
@@ -117,6 +117,13 @@ getCases = create_model(
             description="A list of case field keys to include in the data output. If None, defaults to ['title', 'id'].",
         ),
     ),
+    suite_id=(Optional[str],
+              Field(
+                  default=None,
+                  description="[Optional] Suite id for test cases extraction in case "
+                              "project is in multiple suite mode (setting 3)",
+              ),
+              ),
 )
 
 getCasesByFilter = create_model(
@@ -323,6 +330,30 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
         cls._client = TestRailAPI(url, email, password)
         return super().validate_toolkit(values)
 
+    def _validate_suite_mode_requirements(self, project_id: str, suite_id: Optional[str] = None) -> None:
+        """
+        Validate if project requires suite_id when in multiple suite mode.
+        
+        Args:
+            project_id: The TestRail project ID to check
+            suite_id: The suite ID if provided (optional)
+            custom_error_msg: Custom error message to use (optional)
+        
+        Raises:
+            ToolException: If project is in multiple suite mode and no suite_id is provided
+        """
+        if suite_id:
+            return  # No validation needed if suite_id is already provided
+            
+        try:
+            project = self._client.projects.get_project(project_id=project_id)
+            # 1 for single suite mode, 2 for single suite + baselines, 3 for multiple suites
+            suite_mode = project.get('suite_mode', 1)
+            if suite_mode == 3:
+                raise ToolException("Project is in multiple suite mode, please provide suite_id to extract test cases.")
+        except StatusCodeError as e:
+            logger.warning(f"Unable to check project suite mode: {e}")
+
     def add_cases(self, add_test_cases_data: str):
         """Adds new test cases into Testrail per defined parameters.
                 add_test_cases_data: str - JSON string which includes list of objects with following parameters:
@@ -389,7 +420,8 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
         return f"Extracted test case:\n{str(extracted_case)}"
 
     def get_cases(
-        self, project_id: str, output_format: str = "json", keys: Optional[List[str]] = None
+        self, project_id: str, output_format: str = "json", keys: Optional[List[str]] = None,
+            suite_id: Optional[str] = None
     ) -> Union[str, ToolException]:
         """
         Extracts a list of test cases in the specified format: `json`, `csv`, or `markdown`.
@@ -410,8 +442,15 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
         invalid_keys = [key for key in keys if key not in SUPPORTED_KEYS]
 
         try:
-            extracted_cases = self._client.cases.get_cases(project_id=project_id)
-            cases = extracted_cases.get("cases")
+            # Check if project requires suite_id for multiple suite mode
+            self._validate_suite_mode_requirements(
+                project_id=project_id,
+                suite_id=suite_id
+            )
+            
+            extracted_cases = self._client.cases.get_cases(project_id=project_id, suite_id=suite_id)
+            # support old versions of testrail_api
+            cases = extracted_cases.get("cases") if isinstance(extracted_cases, dict) else extracted_cases
 
             if cases is None:
                 return ToolException("No test cases found in the extracted data.")
@@ -466,10 +505,18 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
                     "json_case_arguments must be a JSON string or dictionary."
                 )
             self._log_tool_event(message=f"Extract test cases per filter {params}", tool_name='get_cases_by_filter')
+            
+            # Check if project requires suite_id when not provided in params
+            suite_id_in_params = params.get('suite_id', None)
+            self._validate_suite_mode_requirements(
+                project_id=project_id,
+                suite_id=str(suite_id_in_params) if suite_id_in_params else None
+            )
+            
             extracted_cases = self._client.cases.get_cases(
                 project_id=project_id, **params
             )
-            self._log_tool_event(message=f"Test cases were extracted", tool_name='get_cases_by_filter')
+            self._log_tool_event(message="Test cases were extracted", tool_name='get_cases_by_filter')
             # support old versions of testrail_api
             cases = extracted_cases.get("cases") if isinstance(extracted_cases, dict) else extracted_cases
 
@@ -542,13 +589,21 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
         self._include_attachments = kwargs.get('include_attachments', False)
         self._skip_attachment_extensions = kwargs.get('skip_attachment_extensions', [])
 
+        def _extract_cases_from_response(response):
+            """Extract cases from API response, supporting both old and new testrail_api versions."""
+            return response.get('cases', []) if isinstance(response, dict) else response
+
         try:
+            # Check if project requires suite_id when not provided
+            self._validate_suite_mode_requirements(project_id=project_id, suite_id=suite_id)
+
             if suite_id:
                 resp = self._client.cases.get_cases(project_id=project_id, suite_id=int(suite_id))
-                cases = resp.get('cases', [])
             else:
                 resp = self._client.cases.get_cases(project_id=project_id)
-                cases = resp.get('cases', [])
+            
+            cases = _extract_cases_from_response(resp)
+            
         except StatusCodeError as e:
             raise ToolException(f"Unable to extract test cases: {e}")
             # Apply filters
@@ -603,11 +658,30 @@ class TestrailAPIWrapper(NonCodeIndexerToolkit):
             case_id = base_data.get("id")
 
             # get a list of attachments for the case
-            attachments = self._client.attachments.get_attachments_for_case_bulk(case_id=case_id)
+            attachments_response = self._client.attachments.get_attachments_for_case(case_id=case_id)
+
+            # Extract attachments from response - handle both old and new API response formats
+            if isinstance(attachments_response, dict) and 'attachments' in attachments_response:
+                attachments = attachments_response['attachments']
+            else:
+                attachments = attachments_response if isinstance(attachments_response, list) else []
 
             # process each attachment to extract its content
             for attachment in attachments:
-                if get_file_extension(attachment['filename']) in self._skip_attachment_extensions:
+                attachment_name = attachment.get('filename') or attachment.get('name')
+                attachment['filename'] = attachment_name
+                
+                # Handle filetype: use existing field if present, otherwise extract from filename
+                if 'filetype' not in attachment or not attachment['filetype']:
+                    file_extension = get_file_extension(attachment_name)
+                    attachment['filetype'] = file_extension.lstrip('.')
+                
+                # Handle is_image: use existing field if present, otherwise check file extension
+                if 'is_image' not in attachment:
+                    file_extension = get_file_extension(attachment_name)
+                    attachment['is_image'] = file_extension in image_extensions
+                
+                if get_file_extension(attachment_name) in self._skip_attachment_extensions:
                     logger.info(f"Skipping attachment {attachment['filename']} with unsupported extension.")
                     continue
 

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.344
+Version: 0.3.345
 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
@@ -82,7 +82,7 @@ Requires-Dist: gitpython==3.1.43; extra == "tools"
 Requires-Dist: atlassian-python-api~=4.0.7; extra == "tools"
 Requires-Dist: jira==3.8.0; extra == "tools"
 Requires-Dist: qtest-swagger-client==0.0.3; extra == "tools"
-Requires-Dist: testrail-api==1.13.2; extra == "tools"
+Requires-Dist: testrail-api==1.13.4; extra == "tools"
 Requires-Dist: azure-devops==7.1.0b4; extra == "tools"
 Requires-Dist: msrest==0.7.1; extra == "tools"
 Requires-Dist: python-graphql-client~=0.4.3; extra == "tools"

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/alita_sdk.egg-info/requires.txt

@@ -88,7 +88,7 @@ gitpython==3.1.43
 atlassian-python-api~=4.0.7
 jira==3.8.0
 qtest-swagger-client==0.0.3
-testrail-api==1.13.2
+testrail-api==1.13.4
 azure-devops==7.1.0b4
 msrest==0.7.1
 python-graphql-client~=0.4.3

{alita_sdk-0.3.344 → alita_sdk-0.3.345}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.344"
+version = "0.3.345"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -33,7 +33,7 @@ email = "ad13box@gmail.com"
 
 [project.optional-dependencies]
 runtime = [ "streamlit>=1.28.0", "langchain_core>=0.3.76,<0.4.0", "langchain>=0.3.22,<0.4.0", "langchain_community>=0.3.7,<0.4.0", "langchain-openai>=0.3.0,<0.4.0", "langchain-anthropic>=0.3.10,<0.4.0", "anthropic>=0.57.0", "langgraph>=0.4.8,<0.5", "langgraph-prebuilt==0.5.2", "langgraph-checkpoint-sqlite~=2.0.0", "langgraph-checkpoint-postgres==2.0.21", "langsmith>=0.3.45", "langchain_chroma>=0.2.2,<0.3.0", "chromadb==0.5.20", "pgvector==0.2.5", "langchain-unstructured~=0.1.6", "langchain-postgres~=0.0.13", "unstructured[local-inference]==0.16.23", "unstructured_pytesseract==0.3.13", "unstructured_inference==0.8.7", "python-pptx==1.0.2", "python-docx==1.1.2", "openpyxl==3.1.2", "pypdf==4.3.1", "pdfminer.six==20240706", "pdf2image==1.16.3", "pikepdf==8.7.1", "docx2txt==0.8", "mammoth==1.9.0", "reportlab==4.2.5", "svglib==1.5.1", "cairocffi==1.7.1", "rlpycairo==0.3.0", "keybert==0.8.3", "sentence-transformers==2.7.0", "gensim==4.3.3", "scipy==1.13.1", "opencv-python==4.11.0.86", "pytesseract==0.3.13", "markdown==3.5.1", "beautifulsoup4==4.12.2", "charset_normalizer==3.3.2", "opentelemetry-exporter-otlp-proto-grpc==1.25.0", "opentelemetry_api==1.25.0", "opentelemetry_instrumentation==0.46b0", "grpcio_status==1.63.0rc1", "protobuf==4.25.7", "langchain-sandbox>=0.0.6",]
-tools = [ "dulwich==0.21.6", "paramiko==3.3.1", "pygithub==2.3.0", "python-gitlab==4.5.0", "gitpython==3.1.43", "atlassian-python-api~=4.0.7", "jira==3.8.0", "qtest-swagger-client==0.0.3", "testrail-api==1.13.2", "azure-devops==7.1.0b4", "msrest==0.7.1", "python-graphql-client~=0.4.3", "zephyr-python-api==0.1.0", "pyral==1.6.0", "boto3>=1.37.23", "azure-core==1.30.2", "azure-identity==1.16.0", "azure-keyvault-keys==4.9.0", "azure-keyvault-secrets==4.8.0", "azure-mgmt-core==1.4.0", "azure-mgmt-resource==23.0.1", "azure-mgmt-storage==21.1.0", "azure-storage-blob==12.23.1", "azure-search-documents==11.5.2", "PyMySQL==1.1.1", "psycopg2-binary==2.9.10", "Office365-REST-Python-Client==2.5.14", "pypdf2~=3.0.1", "FigmaPy==2018.1.0", "pandas==2.2.3", "factor_analyzer==0.5.1", "statsmodels==0.14.4", "tabulate==0.9.0", "tree_sitter==0.20.2", "tree-sitter-languages==1.10.2", "astor~=0.8.1", "markdownify~=1.1.0", "requests_openapi==1.0.5", "duckduckgo_search==5.3.0", "playwright>=1.52.0", "google-api-python-client==2.154.0", "wikipedia==1.4.0", "lxml==5.2.2", "pymupdf==1.24.9", "googlemaps==4.10.0", "yagmail==0.15.293", "pysnc==1.1.10", "shortuuid==1.0.13", "yarl==1.17.1", "langmem==0.0.27", "textract-py3==2.1.1", "slack_sdk==3.35.0", "deltalake==1.0.2", "google_cloud_bigquery==3.34.0",]
+tools = [ "dulwich==0.21.6", "paramiko==3.3.1", "pygithub==2.3.0", "python-gitlab==4.5.0", "gitpython==3.1.43", "atlassian-python-api~=4.0.7", "jira==3.8.0", "qtest-swagger-client==0.0.3", "testrail-api==1.13.4", "azure-devops==7.1.0b4", "msrest==0.7.1", "python-graphql-client~=0.4.3", "zephyr-python-api==0.1.0", "pyral==1.6.0", "boto3>=1.37.23", "azure-core==1.30.2", "azure-identity==1.16.0", "azure-keyvault-keys==4.9.0", "azure-keyvault-secrets==4.8.0", "azure-mgmt-core==1.4.0", "azure-mgmt-resource==23.0.1", "azure-mgmt-storage==21.1.0", "azure-storage-blob==12.23.1", "azure-search-documents==11.5.2", "PyMySQL==1.1.1", "psycopg2-binary==2.9.10", "Office365-REST-Python-Client==2.5.14", "pypdf2~=3.0.1", "FigmaPy==2018.1.0", "pandas==2.2.3", "factor_analyzer==0.5.1", "statsmodels==0.14.4", "tabulate==0.9.0", "tree_sitter==0.20.2", "tree-sitter-languages==1.10.2", "astor~=0.8.1", "markdownify~=1.1.0", "requests_openapi==1.0.5", "duckduckgo_search==5.3.0", "playwright>=1.52.0", "google-api-python-client==2.154.0", "wikipedia==1.4.0", "lxml==5.2.2", "pymupdf==1.24.9", "googlemaps==4.10.0", "yagmail==0.15.293", "pysnc==1.1.10", "shortuuid==1.0.13", "yarl==1.17.1", "langmem==0.0.27", "textract-py3==2.1.1", "slack_sdk==3.35.0", "deltalake==1.0.2", "google_cloud_bigquery==3.34.0",]
 community = [ "retry-extended==0.2.3", "pyobjtojson==0.3", "elitea-analyse==0.1.2",]
 all = [ "alita-sdk[runtime]", "alita-sdk[tools]", "alita-sdk[community]",]
 dev = [ "pytest", "pytest-cov", "black", "flake8", "mypy",]