alita-sdk 0.3.256__tar.gz → 0.3.257__tar.gz

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.256
+Version: 0.3.257
 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 <lifedjik@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

alita_sdk-0.3.257/alita_sdk/configurations/github.py

@@ -0,0 +1,87 @@
+from typing import Optional
+
+from pydantic import BaseModel, ConfigDict, Field, SecretStr, model_validator
+
+
+class GithubConfiguration(BaseModel):
+    model_config = ConfigDict(
+        json_schema_extra={
+            "metadata": {
+                "label": "GitHub",
+                "icon_url": None,
+                "sections": {
+                    "auth": {
+                        "required": False,
+                        "subsections": [
+                            {
+                                "name": "Token",
+                                "fields": ["access_token"]
+                            },
+                            {
+                                "name": "Password",
+                                "fields": ["username", "password"]
+                            },
+                            {
+                                "name": "App private key",
+                                "fields": ["app_id", "app_private_key"]
+                            }
+                        ]
+                    },
+                },
+                "section": "credentials",
+                "type": "github",
+                "categories": ["code repositories"],
+                "extra_categories": ["github", "git", "repository", "code", "version control"],
+            }
+        }
+    )
+
+    base_url: Optional[str] = Field(description="Base API URL", default="https://api.github.com")
+    app_id: Optional[str] = Field(description="Github APP ID", default=None)
+    app_private_key: Optional[SecretStr] = Field(description="Github APP private key", default=None)
+
+    access_token: Optional[SecretStr] = Field(description="Github Access Token", default=None)
+
+    username: Optional[str] = Field(description="Github Username", default=None)
+    password: Optional[SecretStr] = Field(description="Github Password", default=None)
+
+    @model_validator(mode='before')
+    @classmethod
+    def validate_auth_sections(cls, data):
+        if not isinstance(data, dict):
+            return data
+
+        has_token = bool(data.get('access_token') and str(data.get('access_token')).strip())
+        has_password = bool(
+            data.get('username') and str(data.get('username')).strip() and
+            data.get('password') and str(data.get('password')).strip()
+        )
+        has_app_key = bool(
+            data.get('app_id') and str(data.get('app_id')).strip() and
+            data.get('app_private_key') and str(data.get('app_private_key')).strip()
+        )
+
+        # If any method is partially configured, raise exception
+        if (
+                (data.get('username') and not data.get('password')) or
+                (data.get('password') and not data.get('username')) or
+                (data.get('app_id') and not data.get('app_private_key')) or
+                (data.get('app_private_key') and not data.get('app_id'))
+        ):
+            raise ValueError(
+                "Authentication is misconfigured: both username and password, or both app_id and app_private_key, must be provided together."
+            )
+
+        # If all are missing, allow anonymous
+        if not (has_token or has_password or has_app_key):
+            return data
+
+        # If any method is fully configured
+        if has_token or has_password or has_app_key:
+            return data
+
+        raise ValueError(
+            "Authentication is misconfigured: provide either Token (access_token), "
+            "Password (username + password), App private key (app_id + app_private_key), "
+            "or leave all blank for anonymous access."
+        )

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/runtime/clients/client.py

@@ -364,8 +364,8 @@ class AlitaClient:
         return data.content
 
     def delete_artifact(self, bucket_name, artifact_name):
-        url = f'{self.artifact_url}/{bucket_name}/{quote(artifact_name)}'
-        data = requests.delete(url, headers=self.headers, verify=False)
+        url = f'{self.artifact_url}/{bucket_name}'
+        data = requests.delete(url, headers=self.headers, verify=False, params={'filename': quote(artifact_name)})
         return self._process_requst(data)
 
     def _prepare_messages(self, messages: list[BaseMessage]):

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/ado/repos/__init__.py

@@ -95,6 +95,7 @@ class AzureDevOpsReposToolkit(BaseToolkit):
             **kwargs,
             # TODO use ado_repos_configuration fields
             **kwargs['ado_repos_configuration'],
+            **kwargs['ado_repos_configuration']['ado_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
         }
         azure_devops_repos_wrapper = ReposApiWrapper(**wrapper_payload)

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/ado/work_item/ado_wrapper.py

@@ -16,11 +16,6 @@ from pydantic.fields import Field
 
 from alita_sdk.tools.non_code_indexer_toolkit import NonCodeIndexerToolkit
 
-try:
-    from alita_sdk.runtime.langchain.interfaces.llm_processor import get_embeddings
-except ImportError:
-    from alita_sdk.langchain.interfaces.llm_processor import get_embeddings
-
 logger = logging.getLogger(__name__)
 
 create_wi_field = """JSON of the work item fields to create in Azure DevOps, i.e.

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/base_indexer_toolkit.py

@@ -95,7 +95,6 @@ BaseIndexDataParams = create_model(
                          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")),
-    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)),
 )
 
@@ -162,7 +161,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         chunking_config = kwargs.get("chunking_config")
         #
         if clean_index:
-            self._clean_index()
+            self._clean_index(collection_suffix)
         #
         documents = self._base_loader(**kwargs)
         documents = self._reduce_duplicates(documents, collection_suffix)
@@ -173,7 +172,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         return self._save_index(list(documents), collection_suffix=collection_suffix, progress_step=progress_step)
     
     def _apply_loaders_chunkers(self, documents: Generator[Document, None, None], chunking_tool: str=None, chunking_config=None) -> Generator[Document, None, None]:
-        from alita_sdk.tools.chunkers import __confluence_chunkers__ as chunkers
+        from alita_sdk.tools.chunkers import __all__ as chunkers
 
         if chunking_config is None:
             chunking_config = {}

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/bitbucket/tools.py

@@ -134,7 +134,7 @@ class ListBranchesTool(BaseTool):
     name: str = "list_branches_in_repo"
     description: str = """This tool is a wrapper for the Bitbucket API to fetch a list of all branches in the repository. 
     It will return the name of each branch. No input parameters are required."""
-    args_schema: Type[BaseModel] = None
+    args_schema: Type[BaseModel] = create_model("NoInput")
 
     def _run(self):
         try:

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/chunkers/__init__.py

@@ -2,13 +2,15 @@ from .code.codeparser import parse_code_files_for_db
 from .sematic.statistical_chunker import statistical_chunker
 from .sematic.markdown_chunker import markdown_chunker
 from .sematic.proposal_chunker import proposal_chunker
+from .sematic.json_chunker import json_chunker
 from .models import StatisticalChunkerConfig, MarkdownChunkerConfig, ProposalChunkerConfig
 
 __all__ = {
     'code_parser': parse_code_files_for_db,
     'statistical': statistical_chunker,
     'markdown': markdown_chunker,
-    'proposal': proposal_chunker
+    'proposal': proposal_chunker,
+    'json': json_chunker
 }
 
 __confluence_chunkers__ = {

alita_sdk-0.3.257/alita_sdk/tools/chunkers/sematic/json_chunker.py

@@ -0,0 +1,24 @@
+import json
+import logging
+from typing import Generator
+from langchain_text_splitters import RecursiveJsonSplitter
+from langchain_core.documents import Document
+
+def json_chunker(file_content_generator: Generator[Document, None, None], config: dict, *args, **kwargs) -> Generator[Document, None, None]:
+    max_tokens = config.get("max_tokens", 512)
+    for doc in file_content_generator:
+        try:
+            data_dict = json.loads(doc.page_content)
+            chunks = RecursiveJsonSplitter(max_chunk_size=max_tokens).split_json(json_data=data_dict)
+            if len(chunks) == 1:
+                yield doc
+                continue
+            chunk_id = 1
+            for chunk in chunks:
+                metadata = doc.metadata.copy()
+                metadata['chunk_id'] = chunk_id
+                chunk_id += 1
+                yield Document(page_content=json.dumps(chunk), metadata=metadata)
+        except Exception as e:
+            logging.error(f"Failed to chunk document: {e}")
+            yield doc

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/jira/api_wrapper.py

@@ -1237,11 +1237,11 @@ class JiraApiWrapper(BaseVectorStoreToolApiWrapper):
         jql = kwargs.get('jql')
         fields_to_extract = kwargs.get('fields_to_extract')
         fields_to_index = kwargs.get('fields_to_index')
-        include_attachments = kwargs.get('include_attachments', False)
         max_total_issues = kwargs.get('max_total_issues', 1000)
 
-        # set values for skipped attachment extensions
+        # set values for skipped attachment extension
         self._skipped_attachment_extensions = kwargs.get('skip_attachment_extensions', [])
+        self._include_attachments = kwargs.get('include_attachments', False)
         self._included_fields = fields_to_extract.copy() if fields_to_extract else []
 
         try:
@@ -1252,7 +1252,7 @@ class JiraApiWrapper(BaseVectorStoreToolApiWrapper):
             if fields_to_extract:
                 fields.extend(fields_to_extract)
 
-            if include_attachments:
+            if self._include_attachments:
                 fields.append('attachment')
 
             # Use provided JQL query or default to all issues
@@ -1292,36 +1292,36 @@ class JiraApiWrapper(BaseVectorStoreToolApiWrapper):
 
         issue_key = base_document.metadata.get('issue_key')
         # get attachments content
-
-        issue = self._client.issue(issue_key, fields="attachment")
-        attachments = issue.get('fields', {}).get('attachment', [])
-        for attachment in attachments:
-            # get extension
-            ext = f".{attachment['filename'].split('.')[-1].lower()}"
-            if ext not in self._skipped_attachment_extensions:
-                attachment_id = f"attach_{attachment['id']}"
-                base_document.metadata.setdefault(IndexerKeywords.DEPENDENT_DOCS.value, []).append(attachment_id)
-                try:
-                    attachment_content = self._client.get_attachment_content(attachment['id'])
-                except Exception as e:
-                    logger.error(f"Failed to download attachment {attachment['filename']} for issue {issue_key}: {str(e)}")
-                    attachment_content = self._client.get(path=f"secure/attachment/{attachment['id']}/{attachment['filename']}", not_json_response=True)
-                content = load_content_from_bytes(attachment_content, ext, llm=self.llm) if ext not in '.pdf' \
-                    else parse_file_content(file_content=attachment_content, file_name=attachment['filename'], llm=self.llm, is_capture_image=True)
-                if not content:
-                    continue
-                yield Document(page_content=content,
-                               metadata={
-                                   'id': attachment_id,
-                                   'issue_key': issue_key,
-                                   'source': f"{self.base_url}/browse/{issue_key}",
-                                   'filename': attachment['filename'],
-                                   'created': attachment['created'],
-                                   'mimeType': attachment['mimeType'],
-                                   'author': attachment.get('author', {}).get('name'),
-                                   IndexerKeywords.PARENT.value: base_document.metadata.get('id', None),
-                                   'type': 'attachment',
-                               })
+        if self._include_attachments:
+            issue = self._client.issue(issue_key, fields="attachment")
+            attachments = issue.get('fields', {}).get('attachment', [])
+            for attachment in attachments:
+                # get extension
+                ext = f".{attachment['filename'].split('.')[-1].lower()}"
+                if ext not in self._skipped_attachment_extensions:
+                    attachment_id = f"attach_{attachment['id']}"
+                    base_document.metadata.setdefault(IndexerKeywords.DEPENDENT_DOCS.value, []).append(attachment_id)
+                    try:
+                        attachment_content = self._client.get_attachment_content(attachment['id'])
+                    except Exception as e:
+                        logger.error(f"Failed to download attachment {attachment['filename']} for issue {issue_key}: {str(e)}")
+                        attachment_content = self._client.get(path=f"secure/attachment/{attachment['id']}/{attachment['filename']}", not_json_response=True)
+                    content = load_content_from_bytes(attachment_content, ext, llm=self.llm) if ext not in '.pdf' \
+                        else parse_file_content(file_content=attachment_content, file_name=attachment['filename'], llm=self.llm, is_capture_image=True)
+                    if not content:
+                        continue
+                    yield Document(page_content=content,
+                                   metadata={
+                                       'id': attachment_id,
+                                       'issue_key': issue_key,
+                                       'source': f"{self.base_url}/browse/{issue_key}",
+                                       'filename': attachment['filename'],
+                                       'created': attachment['created'],
+                                       'mimeType': attachment['mimeType'],
+                                       'author': attachment.get('author', {}).get('name'),
+                                       IndexerKeywords.PARENT.value: base_document.metadata.get('id', None),
+                                       'type': 'attachment',
+                                   })
 
     def _jql_get_tickets(self, jql, fields="*all", start=0, limit=None, expand=None, validate_query=None):
         """
@@ -1430,9 +1430,9 @@ class JiraApiWrapper(BaseVectorStoreToolApiWrapper):
                                     Field(description="Whether to include attachment content in indexing",
                                           default=False)),
             'max_total_issues': (Optional[int], Field(description="Maximum number of issues to index", default=1000)),
-            'skip_attachment_extensions': (Optional[str], Field(
-                description="Comma-separated list of file extensions to skip when processing attachments",
-                default=None)),
+            'skip_attachment_extensions': (Optional[List[str]], Field(
+                description="List of file extensions to skip when processing attachments: i.e. ['.png', '.jpg']",
+                default=[])),
         }
 
     # def index_data(self,

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/qtest/__init__.py

@@ -35,7 +35,7 @@ class QtestToolkit(BaseToolkit):
             name,
             qtest_configuration=(Optional[QtestConfiguration], Field(description="QTest API token", json_schema_extra={
                 'configuration_types': ['qtest']})),
-            qtest_project_id=(int, Field(description="QTest project id", json_schema_extra={'toolkit_name': True,
+            qtest_project_id=(int, Field(default=None, description="QTest project id", json_schema_extra={'toolkit_name': True,
                                                                                             'max_toolkit_length': QtestToolkit.toolkit_max_length})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),

alita_sdk-0.3.257/alita_sdk/tools/utils/available_tools_decorator.py

@@ -0,0 +1,6 @@
+def extend_with_parent_available_tools(method):
+    def wrapper(self, *args, **kwargs):
+        child_tools = method(self, *args, **kwargs)
+        parent_tools = super(self.__class__, self).get_available_tools()
+        return parent_tools + child_tools
+    return wrapper

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk/tools/zephyr_essential/api_wrapper.py

@@ -1,5 +1,6 @@
 import json
-from typing import Optional, Generator
+import logging
+from typing import Optional, Generator, Literal
 from pydantic import model_validator, create_model, Field, SecretStr, PrivateAttr
 
 from .client import ZephyrEssentialAPI
@@ -7,7 +8,11 @@ from ..elitea_base import extend_with_vector_tools, BaseVectorStoreToolApiWrappe
 from langchain_core.documents import Document
 from langchain_core.tools import ToolException
 
-class ZephyrEssentialApiWrapper(BaseVectorStoreToolApiWrapper):
+from ..non_code_indexer_toolkit import NonCodeIndexerToolkit
+from ..utils.available_tools_decorator import extend_with_parent_available_tools
+
+
+class ZephyrEssentialApiWrapper(NonCodeIndexerToolkit):
     token: SecretStr
     _client: ZephyrEssentialAPI = PrivateAttr()
 
@@ -22,7 +27,7 @@ class ZephyrEssentialApiWrapper(BaseVectorStoreToolApiWrapper):
             base_url=base_url,
             token=token
         )
-        return values
+        return super().validate_toolkit(values)
 
     def list_test_cases(self, project_key: Optional[str] = None, folder_id: Optional[str] = None, max_results: int = None, start_at: int = None):
         """List test cases with optional filters."""
@@ -229,6 +234,12 @@ class ZephyrEssentialApiWrapper(BaseVectorStoreToolApiWrapper):
         except json.JSONDecodeError as e:
             raise ValueError(f"Invalid JSON string: {str(e)}")
 
+    def _index_tool_params(self):
+        return {
+            'chunking_tool':(Literal[None, 'json'],
+                           Field(description="Name of chunking tool", default='json'))
+        }
+
     def _base_loader(self, **kwargs) -> Generator[Document, None, None]:
         try:
             test_cases = self.list_test_cases()
@@ -236,36 +247,34 @@ class ZephyrEssentialApiWrapper(BaseVectorStoreToolApiWrapper):
             raise ToolException(f"Unable to extract test cases: {e}")
 
         for case in test_cases:
-            case['type'] = "TEST_CASE"
             metadata = {
                 k: v for k, v in case.items()
                 if isinstance(v, (str, int, float, bool, list, dict))
             }
-
-            yield Document(page_content=json.dumps(case), metadata=metadata)
-
-    def _process_document(self, document: Document) -> Generator[Document, None, None]:
-        try:
-            base_data = json.loads(document.page_content)
-
-            if base_data['type'] and base_data['type'] == "TEST_CASE":
-                additional_content = self._process_test_case(base_data)
-                base_data['test_case_content'] = additional_content
-
-            document.page_content = json.dumps(base_data)
-        except json.JSONDecodeError as e:
-            raise ToolException(f"Failed to decode JSON from document: {e}")
-
-    def _process_test_case(self, case):
-        steps = self.get_test_case_test_steps(case['key'])
-        script = self.get_test_case_test_script(case['key'])
+            metadata['type'] = "TEST_CASE"
+
+            yield Document(page_content="", metadata=metadata)
+
+    def _extend_data(self, documents: Generator[Document, None, None]) -> Generator[Document, None, None]:
+        for document in documents:
+            try:
+                if document.metadata['type'] and document.metadata['type'] == "TEST_CASE":
+                    additional_content = self._process_test_case(document.metadata['key'])
+                    document.page_content = json.dumps(additional_content)
+            except json.JSONDecodeError as e:
+                logging.error(f"Failed to decode JSON from document: {e}")
+            yield document
+
+    def _process_test_case(self, key):
+        steps = self.get_test_case_test_steps(key)
+        script = self.get_test_case_test_script(key)
         additional_content = {
             "steps": "" if isinstance(steps, ToolException) else steps,
             "script": "" if isinstance(script, ToolException) else script,
         }
         return additional_content
 
-    @extend_with_vector_tools
+    @extend_with_parent_available_tools
     def get_available_tools(self):
         return [
             {

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.256
+Version: 0.3.257
 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 <lifedjik@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/alita_sdk.egg-info/SOURCES.txt

@@ -202,6 +202,7 @@ alita_sdk/tools/chunkers/code/treesitter/treesitter_rs.py
 alita_sdk/tools/chunkers/code/treesitter/treesitter_ts.py
 alita_sdk/tools/chunkers/sematic/__init__.py
 alita_sdk/tools/chunkers/sematic/base.py
+alita_sdk/tools/chunkers/sematic/json_chunker.py
 alita_sdk/tools/chunkers/sematic/markdown_chunker.py
 alita_sdk/tools/chunkers/sematic/proposal_chunker.py
 alita_sdk/tools/chunkers/sematic/statistical_chunker.py
@@ -320,6 +321,7 @@ alita_sdk/tools/testio/api_wrapper.py
 alita_sdk/tools/testrail/__init__.py
 alita_sdk/tools/testrail/api_wrapper.py
 alita_sdk/tools/utils/__init__.py
+alita_sdk/tools/utils/available_tools_decorator.py
 alita_sdk/tools/utils/content_parser.py
 alita_sdk/tools/vector_adapters/VectorStoreAdapter.py
 alita_sdk/tools/vector_adapters/__init__.py

{alita_sdk-0.3.256 → alita_sdk-0.3.257}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.256"
+version = "0.3.257"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"

alita_sdk-0.3.256/alita_sdk/configurations/github.py

@@ -1,45 +0,0 @@
-from typing import Optional
-
-from pydantic import BaseModel, ConfigDict, Field, SecretStr
-
-
-class GithubConfiguration(BaseModel):
-    model_config = ConfigDict(
-        json_schema_extra={
-            "metadata": {
-                "label": "GitHub",
-                "icon_url": None,
-                "sections": {
-                    "auth": {
-                        "required": False,
-                        "subsections": [
-                            {
-                                "name": "Token",
-                                "fields": ["access_token"]
-                            },
-                            {
-                                "name": "Password",
-                                "fields": ["username", "password"]
-                            },
-                            {
-                                "name": "App private key",
-                                "fields": ["app_id", "app_private_key"]
-                            }
-                        ]
-                    },
-                },
-                "section": "credentials",
-                "type": "github",
-                "categories": ["code repositories"],
-                "extra_categories": ["github", "git", "repository", "code", "version control"],
-            }
-        }
-    )
-    base_url: Optional[str] = Field(description="Base API URL", default="https://api.github.com")
-    app_id: Optional[str] = Field(description="Github APP ID", default=None)
-    app_private_key: Optional[SecretStr] = Field(description="Github APP private key", default=None)
-
-    access_token: Optional[SecretStr] = Field(description="Github Access Token", default=None)
-
-    username: Optional[str] = Field(description="Github Username", default=None)
-    password: Optional[SecretStr] = Field(description="Github Password", default=None)