alita-sdk 0.3.241__tar.gz → 0.3.243__tar.gz

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.241
+Version: 0.3.243
 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-0.3.241 → alita_sdk-0.3.243}/alita_sdk/runtime/langchain/document_loaders/AlitaCSVLoader.py

@@ -13,14 +13,15 @@
 # limitations under the License.
 
 from typing import List, Optional, Iterator
-from charset_normalizer import from_path
+from charset_normalizer import from_path, from_bytes
 from csv import DictReader
 from .AlitaTableLoader import AlitaTableLoader
 from typing import Any
 
 class AlitaCSVLoader(AlitaTableLoader):
     def __init__(self,
-                 file_path: str,
+                 file_path: str = None,
+                 file_content: bytes = None,
                  encoding: Optional[str] = 'utf-8',
                  autodetect_encoding: bool = True,
                  json_documents: bool = True,
@@ -28,11 +29,14 @@ class AlitaCSVLoader(AlitaTableLoader):
                  columns: Optional[List[str]] = None,
                  cleanse: bool = True,
                  **kwargs):
-        super().__init__(file_path=file_path, json_documents=json_documents, columns=columns, raw_content=raw_content, cleanse=cleanse)
+        super().__init__(file_path=file_path, file_content=file_content, json_documents=json_documents, columns=columns, raw_content=raw_content, cleanse=cleanse)
         self.encoding = encoding
         self.autodetect_encoding = autodetect_encoding
-        if autodetect_encoding:
-            self.encoding = from_path(self.file_path).best().encoding
+        if self.file_path:
+            if autodetect_encoding:
+                self.encoding = from_path(self.file_path).best().encoding
+        else:
+            self.encoding = from_bytes(self.file_content).best().encoding
 
     def read_lazy(self) -> Iterator[dict]:
         with open(self.file_path, 'r', encoding=self.encoding) as fd:
@@ -43,7 +47,11 @@ class AlitaCSVLoader(AlitaTableLoader):
                 yield row
 
     def read(self) -> Any:
-        with open(self.file_path, 'r', encoding=self.encoding) as fd:
-            if self.raw_content:
-                return [fd.read()]
-            return list(DictReader(fd))
+        if self.file_path:
+            with open(self.file_path, 'r', encoding=self.encoding) as fd:
+                if self.raw_content:
+                    return [fd.read()]
+                return list(DictReader(fd))
+        else:
+            super.row_content = True
+            return self.file_content

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/runtime/langchain/document_loaders/AlitaTableLoader.py

@@ -22,7 +22,8 @@ from ..tools.log import print_log
 
 class AlitaTableLoader(BaseLoader):
     def __init__(self,
-                 file_path: str,
+                 file_path: str = None,
+                 file_content: bytes = None,
                  json_documents: bool = True,
                  raw_content: bool = False,
                  columns: Optional[List[str]] = None,
@@ -30,6 +31,7 @@ class AlitaTableLoader(BaseLoader):
 
         self.raw_content = raw_content
         self.file_path = file_path
+        self.file_content = file_content
         self.json_documents = json_documents
         self.columns = columns
         self.cleanse = cleanse
@@ -63,6 +65,11 @@ class AlitaTableLoader(BaseLoader):
                 "source": f'{self.file_path}:{idx+1}',
                 "table_source": self.file_path,
             }
+            if len(docs) == 0:
+                header_metadata = metadata.copy()
+                header_metadata["header"] = "true"
+                header = "\t".join([str(value) for value in row.keys()])
+                docs.append(Document(page_content=header, metadata=header_metadata))
             if self.raw_content:
                 docs.append(Document(page_content=row, metadata=metadata))
                 continue

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/ado/__init__.py

@@ -18,8 +18,7 @@ def get_tools(tool_type, tool):
         "pgvector_configuration": tool['settings'].get('pgvector_configuration', {}),
         "collection_name": tool['toolkit_name'],
         "doctype": 'doc',
-        "embedding_model": "HuggingFaceEmbeddings",
-        "embedding_model_params": {"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        "embedding_configuration": tool['settings'].get('embedding_configuration', {}),
         "vectorstore_type": "PGVector"
     }
     if tool_type == 'ado_plans':

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/ado/repos/__init__.py

@@ -24,10 +24,9 @@ def _get_toolkit(tool) -> BaseToolkit:
         active_branch=tool['settings'].get('active_branch', ""),
         toolkit_name=tool['settings'].get('toolkit_name', ""),
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=tool['toolkit_name'],
         doctype='code',
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector",
     )
 
@@ -110,6 +109,7 @@ class AzureDevOpsReposToolkit(BaseToolkit):
             # TODO use ado_repos_configuration fields
             **kwargs['ado_repos_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         azure_devops_repos_wrapper = ReposApiWrapper(**wrapper_payload)
         available_tools = azure_devops_repos_wrapper.get_available_tools()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/ado/test_plan/__init__.py

@@ -92,6 +92,7 @@ class AzureDevOpsPlansToolkit(BaseToolkit):
             # TODO use ado_configuration fields in TestPlanApiWrapper
             **kwargs['ado_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         azure_devops_api_wrapper = TestPlanApiWrapper(**wrapper_payload)
         available_tools = azure_devops_api_wrapper.get_available_tools()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/ado/wiki/__init__.py

@@ -90,6 +90,7 @@ class AzureDevOpsWikiToolkit(BaseToolkit):
             # TODO use ado_configuration fields in AzureDevOpsApiWrapper
             **kwargs['ado_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         azure_devops_api_wrapper = AzureDevOpsApiWrapper(**wrapper_payload)
         available_tools = azure_devops_api_wrapper.get_available_tools()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/ado/work_item/__init__.py

@@ -90,6 +90,7 @@ class AzureDevOpsWorkItemsToolkit(BaseToolkit):
             # TODO use ado_configuration fields in AzureDevOpsApiWrapper
             **kwargs['ado_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         azure_devops_api_wrapper = AzureDevOpsApiWrapper(**wrapper_payload)
         available_tools = azure_devops_api_wrapper.get_available_tools()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/bitbucket/__init__.py

@@ -31,8 +31,7 @@ def get_tools(tool):
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
         collection_name=str(tool['toolkit_name']),
         doctype='code',
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         vectorstore_type="PGVector",
         toolkit_name=tool.get('toolkit_name')
     ).get_tools()
@@ -101,6 +100,7 @@ class AlitaBitbucketToolkit(BaseToolkit):
             # TODO use bitbucket_configuration fields
             **kwargs['bitbucket_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         bitbucket_api_wrapper = BitbucketAPIWrapper(**wrapper_payload)
         available_tools: List[Dict] = __all__

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/confluence/__init__.py

@@ -30,8 +30,7 @@ def get_tools(tool):
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
         collection_name=str(tool['toolkit_name']),
         doctype='doc',
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         vectorstore_type="PGVector"
     ).get_tools()
 
@@ -125,6 +124,7 @@ class ConfluenceToolkit(BaseToolkit):
             # TODO use confluence_configuration fields
             **kwargs['confluence_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         confluence_api_wrapper = ConfluenceAPIWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, ConfluenceToolkit.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/figma/__init__.py

@@ -27,8 +27,7 @@ def get_tools(tool):
             pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
             collection_name=str(tool['toolkit_name']),
             doctype='doc',
-            embedding_model="HuggingFaceEmbeddings",
-            embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+            embedding_configuration=tool['settings'].get('embedding_configuration', {}),
             vectorstore_type="PGVector"
         )
         .get_tools()
@@ -98,6 +97,7 @@ class FigmaToolkit(BaseToolkit):
         wrapper_payload = {
             **kwargs,
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         figma_api_wrapper = FigmaApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/github/__init__.py

@@ -26,8 +26,7 @@ def _get_toolkit(tool) -> BaseToolkit:
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
         collection_name=str(tool['toolkit_name']),
         doctype='code',
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         vectorstore_type="PGVector",
         toolkit_name=tool.get('toolkit_name')
     )
@@ -84,6 +83,7 @@ class AlitaGitHubToolkit(BaseToolkit):
             # TODO use github_configuration fields
             **kwargs['github_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         github_api_wrapper = AlitaGitHubAPIWrapper(**wrapper_payload)
         available_tools: List[Dict] = github_api_wrapper.get_available_tools()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/gitlab/__init__.py

@@ -28,8 +28,7 @@ def get_tools(tool):
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
         collection_name=str(tool['toolkit_name']),
         doctype='code',
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         vectorstore_type="PGVector",
         toolkit_name=tool.get('toolkit_name')
     ).get_tools()
@@ -85,6 +84,7 @@ class AlitaGitlabToolkit(BaseToolkit):
             # TODO use gitlab_configuration fields
             **kwargs['gitlab_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         gitlab_api_wrapper = GitLabAPIWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/jira/__init__.py

@@ -20,15 +20,15 @@ def get_tools(tool):
         jira_configuration=tool['settings']['jira_configuration'],
         limit=tool['settings'].get('limit', 5),
         labels=parse_list(tool['settings'].get('labels', [])),
+        custom_headers=tool['settings'].get('custom_headers', {}),
         additional_fields=tool['settings'].get('additional_fields', []),
         verify_ssl=tool['settings'].get('verify_ssl', True),
         # indexer settings
         llm=tool['settings'].get('llm', None),
         alita=tool['settings'].get('alita', None),
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=str(tool['toolkit_name']),
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector",
         toolkit_name=tool.get('toolkit_name')
     ).get_tools()
@@ -66,12 +66,14 @@ class JiraToolkit(BaseToolkit):
         model = create_model(
             name,
             cloud=(bool, Field(description="Hosting Option", json_schema_extra={'configuration': True})),
-            limit=(int, Field(description="Limit issues")),
+            limit=(int, Field(description="Limit issues. Default is 5", gt=0, default=5)),
             labels=(Optional[str], Field(
                 description="List of comma separated labels used for labeling of agent's created or updated entities",
                 default=None,
                 examples="alita,elitea;another-label"
             )),
+            # optional field for custom headers as dictionary
+            custom_headers=(Optional[dict], Field(description="Custom headers for API requests", default=None)),
             verify_ssl=(bool, Field(description="Verify SSL", default=True)),
             additional_fields=(Optional[str], Field(description="Additional fields", default="")),
             jira_configuration=(Optional[JiraConfiguration], Field(description="Jira Configuration", json_schema_extra={'configuration_types': ['jira']})),
@@ -103,6 +105,7 @@ class JiraToolkit(BaseToolkit):
             # TODO use jira_configuration fields
             **kwargs['jira_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         jira_api_wrapper = JiraApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/jira/api_wrapper.py

@@ -436,6 +436,11 @@ class JiraApiWrapper(BaseVectorStoreToolApiWrapper):
             cls._client = Jira(url=url, token=token, cloud=cloud, verify_ssl=values['verify_ssl'], api_version=api_version)
         else:
             cls._client = Jira(url=url, username=username, password=api_key, cloud=cloud, verify_ssl=values['verify_ssl'], api_version=api_version)
+        custom_headers = values.get('custom_headers', {})
+        logger.info(f"Jira tool: custom headers length: {len(custom_headers)}")
+        for header, value in custom_headers.items():
+            cls._client._update_header(header, value)
+
         cls.llm=values.get('llm')
         return values
 

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/sharepoint/__init__.py

@@ -5,6 +5,7 @@ from pydantic import create_model, BaseModel, ConfigDict, Field, SecretStr
 from .api_wrapper import SharepointApiWrapper
 from ..base.tool import BaseAction
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
 name = "sharepoint"
@@ -21,9 +22,8 @@ def get_tools(tool):
         alita=tool['settings'].get('alita', None),
         # indexer settings
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=str(tool['toolkit_name']),
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector")
             .get_tools())
 
@@ -44,10 +44,9 @@ class SharepointToolkit(BaseToolkit):
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             # indexer settings
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(description="PgVector Configuration", json_schema_extra={'configuration_types': ['pgvector']})),
-
             # embedder settings
-            embedding_model=(str, Field(description="Embedding model: i.e. 'HuggingFaceEmbeddings', etc.", default="HuggingFaceEmbeddings")),
-            embedding_model_params=(dict, Field(description="Embedding model parameters: i.e. `{'model_name': 'sentence-transformers/all-MiniLM-L6-v2'}", default={"model_name": "sentence-transformers/all-MiniLM-L6-v2"})),
+            embedding_configuration=(Optional[EmbeddingConfiguration], Field(description="Embedding configuration.",
+                                                                              json_schema_extra={'configuration_types': ['embedding']})),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {
                     "label": "Sharepoint", "icon_url": "sharepoint.svg",
@@ -63,6 +62,7 @@ class SharepointToolkit(BaseToolkit):
         wrapper_payload = {
             **kwargs,
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         sharepoint_api_wrapper = SharepointApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/sharepoint/api_wrapper.py

@@ -170,7 +170,7 @@ class SharepointApiWrapper(BaseVectorStoreToolApiWrapper):
         except Exception as e:
             logging.error(f"Failed while parsing the file '{document.metadata['Path']}': {e}")
         if isinstance(doc_content, dict):
-            for page, content in doc_content:
+            for page, content in doc_content.items():
                 new_metadata = document.metadata
                 new_metadata['page'] = page
                 yield Document(page_content=str(content), metadata=new_metadata)

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/testrail/__init__.py

@@ -24,9 +24,8 @@ def get_tools(tool):
 
         # indexer settings
         pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=f"{tool.get('toolkit_name')}",
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector"
     ).get_tools()
 
@@ -77,6 +76,7 @@ class TestrailToolkit(BaseToolkit):
             # TODO use testrail_configuration fields
             **kwargs['testrail_configuration'],
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         testrail_api_wrapper = TestrailAPIWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/utils/content_parser.py

@@ -90,7 +90,9 @@ def parse_file_content(file_name=None, file_content=None, is_capture_image: bool
         "llm": llm,
         "page_number": page_number,
         "sheet_name": sheet_name,
-        "excel_by_sheets": excel_by_sheets
+        "excel_by_sheets": excel_by_sheets,
+        "row_content": True,
+        "json_documents": False
     })
     loader = loader_object['class'](**loader_kwargs)
 
@@ -135,6 +137,8 @@ def load_content(file_path: str, extension: str = None, loader_extra_config: dic
             loader_kwargs.update(loader_extra_config)
         if loader_config['is_multimodal_processing'] and llm:
             loader_kwargs.update({'llm': llm})
+        if "file_path" in loader_kwargs:
+            del loader_kwargs["file_path"]
 
         loader = loader_cls(file_path, **loader_kwargs)
         documents = loader.load()

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/xray/__init__.py

@@ -27,10 +27,9 @@ def get_tools(tool):
         alita=tool['settings'].get('alita', None),
 
         # indexer settings
-        connection_string=tool['settings'].get('connection_string', None),
+        pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=str(tool['toolkit_name']),
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector"
     ).get_tools()
 
@@ -76,6 +75,7 @@ class XrayToolkit(BaseToolkit):
             # Use xray_configuration fields
             **kwargs.get('xray_configuration', {}),
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         xray_api_wrapper = XrayApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/zephyr_enterprise/__init__.py

@@ -21,10 +21,9 @@ def get_tools(tool):
         alita=tool['settings'].get('alita', None),
 
         # indexer settings
-        connection_string=tool['settings'].get('connection_string', None),
+        pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         collection_name=str(tool['toolkit_name']),
-        embedding_model="HuggingFaceEmbeddings",
-        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector"
     ).get_tools()
 
@@ -65,6 +64,7 @@ class ZephyrEnterpriseToolkit(BaseToolkit):
             # Use zephyr_configuration fields
             **kwargs.get('zephyr_configuration', {}),
             **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
         }
         zephyr_api_wrapper = ZephyrApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk/tools/zephyr_essential/__init__.py

@@ -20,10 +20,9 @@ def get_tools(tool):
         alita=tool['settings'].get('alita', None),
 
         # indexer settings
-        connection_string = tool['settings'].get('connection_string', None),
         collection_name=str(tool['toolkit_name']),
-        embedding_model = "HuggingFaceEmbeddings",
-        embedding_model_params = {"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_configuration=tool['settings'].get('embedding_configuration', {}),
         vectorstore_type = "PGVector"
     ).get_tools()
 
@@ -55,7 +54,14 @@ class ZephyrEssentialToolkit(BaseToolkit):
 
     @classmethod
     def get_toolkit(cls, selected_tools: list[str] | None = None, toolkit_name: Optional[str] = None, **kwargs):
-        zephyr_api_wrapper = ZephyrEssentialApiWrapper(**kwargs)
+        if selected_tools is None:
+            selected_tools = []
+        wrapper_payload = {
+            **kwargs,
+            **(kwargs.get('pgvector_configuration') or {}),
+            **(kwargs.get('embedding_configuration') or {}),
+        }
+        zephyr_api_wrapper = ZephyrEssentialApiWrapper(**wrapper_payload)
         prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''
         available_tools = zephyr_api_wrapper.get_available_tools()
         tools = []

{alita_sdk-0.3.241 → alita_sdk-0.3.243}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.241
+Version: 0.3.243
 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-0.3.241 → alita_sdk-0.3.243}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.241"
+version = "0.3.243"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"