alita-sdk 0.3.232__tar.gz → 0.3.234__tar.gz

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.232
+Version: 0.3.234
 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-0.3.232 → alita_sdk-0.3.234}/alita_sdk/configurations/confluence.py

@@ -31,6 +31,7 @@ class ConfluenceConfiguration(BaseModel):
             }
         }
     )
+    base_url: str = Field(description="Confluence URL")
     username: Optional[str] = Field(description="Confluence Username", default=None)
     api_key: Optional[SecretStr] = Field(description="Confluence API Key", default=None)
-    token: Optional[SecretStr] = Field(description="Confluence Token", default=None)
+    token: Optional[SecretStr] = Field(description="Confluence Token", default=None)

alita_sdk-0.3.234/alita_sdk/configurations/embedding.py

@@ -0,0 +1,19 @@
+from pydantic import BaseModel, ConfigDict, Field, SecretStr
+
+
+class EmbeddingConfiguration(BaseModel):
+    model_config = ConfigDict(
+        json_schema_extra={
+            "metadata": {
+                "label": "Embedding Vector Storage",
+                "icon_url": None,
+                "section": "vectorstorage",
+                "type": "embedding"
+            }
+        }
+    )
+    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"})

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/configurations/slack.py

@@ -15,11 +15,11 @@ class SlackConfiguration(BaseModel):
                         "subsections": [
                             {
                                 "name": "Bot Token",
-                                "fields": ["bot_token"]
+                                "fields": ["name"]
                             },
                             {
                                 "name": "User Token",
-                                "fields": ["user_token"]
+                                "fields": ["slack_token"]
                             }
                         ]
                     },

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/configurations/testrail.py

@@ -16,5 +16,6 @@ class TestRailConfiguration(BaseModel):
             }
         }
     )
-    email: Optional[str] = Field(description="TestRail Email", default=None)
-    password: Optional[SecretStr] = Field(description="TestRail Password", default=None)
+    url: str = Field(description="Testrail URL")
+    email: str = Field(description="TestRail Email")
+    password: SecretStr = Field(description="TestRail Password")

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/runtime/tools/vectorstore.py

@@ -231,13 +231,13 @@ class VectorStoreWrapper(BaseToolApiWrapper):
             tool_name="_clean_collection"
         )
 
-    def _get_indexed_data(self):
+    def _get_indexed_data(self, collection_name: str):
         """ Get all indexed data from vectorstore for non-code content """
-        return self.vector_adapter.get_indexed_data(self)
+        return self.vector_adapter.get_indexed_data(self, collection_name)
 
-    def _get_code_indexed_data(self) -> Dict[str, Dict[str, Any]]:
+    def _get_code_indexed_data(self, collection_suffix: str) -> Dict[str, Dict[str, Any]]:
         """ Get all indexed data from vectorstore for code content """
-        return self.vector_adapter.get_code_indexed_data(self)
+        return self.vector_adapter.get_code_indexed_data(self, collection_suffix)
 
     def _add_to_collection(self, entry_id, new_collection_value):
         """Add a new collection name to the `collection` key in the `metadata` column."""
@@ -255,7 +255,7 @@ class VectorStoreWrapper(BaseToolApiWrapper):
     ) -> List[Any]:
         """Generic duplicate reduction logic for documents."""
         self._log_data(log_msg, tool_name="index_documents")
-        indexed_data = get_indexed_data()
+        indexed_data = get_indexed_data(collection_suffix)
         indexed_keys = set(indexed_data.keys())
         if not indexed_keys:
             self._log_data("Vectorstore is empty, indexing all incoming documents", tool_name="index_documents")

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/ado/repos/__init__.py

@@ -6,6 +6,7 @@ from pydantic import BaseModel, Field, create_model
 import requests
 
 from ....configurations.ado import AdoReposConfiguration
+from ....configurations.embedding import EmbeddingConfiguration
 from ....configurations.pgvector import PgVectorConfiguration
 from ...base.tool import BaseAction
 from .repos_wrapper import ReposApiWrapper
@@ -54,11 +55,8 @@ class AzureDevOpsReposToolkit(BaseToolkit):
             # 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']})),
 
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra': {'metadata':

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/ado/test_plan/__init__.py

@@ -5,6 +5,7 @@ from pydantic import create_model, BaseModel, Field
 
 import requests
 from ....configurations.ado import AdoConfiguration
+from ....configurations.embedding import EmbeddingConfiguration
 from ....configurations.pgvector import PgVectorConfiguration
 from .test_plan_wrapper import TestPlanApiWrapper
 from ...base.tool import BaseAction
@@ -31,11 +32,9 @@ class AzureDevOpsPlansToolkit(BaseToolkit):
             # 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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra': {'metadata':
                 {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/ado/wiki/__init__.py

@@ -5,6 +5,7 @@ from pydantic import create_model, BaseModel, Field
 
 import requests
 from ....configurations.ado import AdoConfiguration
+from ....configurations.embedding import EmbeddingConfiguration
 from ....configurations.pgvector import PgVectorConfiguration
 from ...base.tool import BaseAction
 from ...utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, check_connection_response
@@ -31,11 +32,9 @@ class AzureDevOpsWikiToolkit(BaseToolkit):
             # 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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/ado/work_item/__init__.py

@@ -5,6 +5,7 @@ from pydantic import create_model, BaseModel, Field
 
 import requests
 from ....configurations.ado import AdoConfiguration
+from ....configurations.embedding import EmbeddingConfiguration
 from ....configurations.pgvector import PgVectorConfiguration
 from ...base.tool import BaseAction
 from ...utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, check_connection_response
@@ -32,11 +33,9 @@ class AzureDevOpsWorkItemsToolkit(BaseToolkit):
             # 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__={
                 'json_schema_extra': {
                     'metadata': {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/bitbucket/__init__.py

@@ -9,6 +9,7 @@ from langchain_core.tools import BaseTool
 from pydantic import BaseModel, Field, ConfigDict, create_model
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, check_connection_response
 from ...configurations.bitbucket import BitbucketConfiguration
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 import requests
 
@@ -58,8 +59,9 @@ class AlitaBitbucketToolkit(BaseToolkit):
             bitbucket_configuration=(Optional[BitbucketConfiguration], Field(description="Bitbucket Configuration", json_schema_extra={'configuration_types': ['bitbucket']})),
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(description="PgVector Configuration", default={'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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra=
             {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/confluence/__init__.py

@@ -6,6 +6,7 @@ from ..base.tool import BaseAction
 from pydantic import create_model, BaseModel, ConfigDict, Field
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, parse_list, check_connection_response
 from ...configurations.confluence import ConfluenceConfiguration
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 import requests
 
@@ -66,7 +67,6 @@ class ConfluenceToolkit(BaseToolkit):
 
         model = create_model(
             name,
-            base_url=(str, Field(description="Confluence URL", json_schema_extra={'configuration': True, 'configuration_title': True})),
             space=(str, Field(description="Space", json_schema_extra={'toolkit_name': True,
                                                                                     'max_toolkit_length': ConfluenceToolkit.toolkit_max_length})),
             cloud=(bool, Field(description="Hosting Option", json_schema_extra={'configuration': True})),
@@ -82,8 +82,10 @@ class ConfluenceToolkit(BaseToolkit):
             max_retry_seconds=(int, Field(description="Max retry, sec", default=60)),
             confluence_configuration=(Optional[ConfluenceConfiguration], Field(description="Confluence Configuration", json_schema_extra={'configuration_types': ['confluence']})),
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(description="PgVector Configuration", json_schema_extra={'configuration_types': ['pgvector']})),
-            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"})),
+            # embedder settings
+            embedding_configuration=(Optional[EmbeddingConfiguration], Field(description="Embedding configuration.",
+                                                                             json_schema_extra={'configuration_types': [
+                                                                                 'embedding']})),
 
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/elitea_base.py

@@ -118,7 +118,7 @@ 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['','markdown', 'statistical', 'proposal'], Field(description="Name of chunking tool", default=None)),
+    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)),
 )
 
@@ -397,7 +397,7 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
             reranking_config=reranking_config,
             extended_search=extended_search
         )
-        return f"Found {len(found_docs)} documents matching the query\n{json.dumps(found_docs, indent=4)}" if found_docs else "No documents found matching the query."
+        return found_docs if found_docs else f"No documents found by query '{query}' and filter '{filter}'"
 
     def stepback_search_index(self,
                      query: str,

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/figma/__init__.py

@@ -6,6 +6,7 @@ from pydantic import BaseModel, ConfigDict, Field, create_model, SecretStr
 from ..base.tool import BaseAction
 from .api_wrapper import FigmaApiWrapper, GLOBAL_LIMIT
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
 name = "figma"
@@ -58,8 +59,9 @@ class FigmaToolkit(BaseToolkit):
             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": {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/github/__init__.py

@@ -7,6 +7,7 @@ from .api_wrapper import AlitaGitHubAPIWrapper
 from .tool import GitHubAction
 
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.github import GithubConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
@@ -66,9 +67,10 @@ class AlitaGitHubToolkit(BaseToolkit):
                                                                                        'max_toolkit_length': AlitaGitHubToolkit.toolkit_max_length})),
             active_branch=(Optional[str], Field(description="Active branch", default="main")),
             base_branch=(Optional[str], Field(description="Github Base branch", default="main")),
-            # indexer 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"})),
+            # embedder settings
+            embedding_configuration=(Optional[EmbeddingConfiguration], Field(description="Embedding configuration.",
+                                                                             json_schema_extra={'configuration_types': [
+                                                                                 'embedding']})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools}))
         )

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/gitlab/__init__.py

@@ -8,6 +8,7 @@ from pydantic.fields import Field
 
 from .api_wrapper import GitLabAPIWrapper
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.gitlab import GitlabConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
@@ -51,8 +52,9 @@ class AlitaGitlabToolkit(BaseToolkit):
             # 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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/jira/__init__.py

@@ -6,6 +6,7 @@ from pydantic import create_model, BaseModel, ConfigDict, Field
 import requests
 
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, parse_list, check_connection_response
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.jira import JiraConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
@@ -86,8 +87,9 @@ class JiraToolkit(BaseToolkit):
             jira_configuration=(Optional[JiraConfiguration], Field(description="Jira Configuration", json_schema_extra={'configuration_types': ['jira']})),
             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']})),
 
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/slack/__init__.py

@@ -55,7 +55,14 @@ class SlackToolkit(BaseToolkit):
              channel_id=(Optional[str], Field(default=None, description="Channel ID", json_schema_extra={'configuration': True})),
              selected_tools=(List[Literal[tuple(selected_tools)]],
                              Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
-             __config__={'json_schema_extra': {'metadata': {"label": "Slack", "icon_url": "slack-icon.svg"}}}
+             __config__={'json_schema_extra': {
+                'metadata': {
+                    "label": "Slack",
+                    "icon_url": "slack-icon.svg",
+                    "categories": ["communication"],
+                    "extra_categories": ["slack", "chat", "messaging", "collaboration"],
+                }
+            }}
          )
          model.check_connection = check_connection
          return model

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/testrail/__init__.py

@@ -7,6 +7,7 @@ import requests
 from .api_wrapper import TestrailAPIWrapper
 from ..base.tool import BaseAction
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, check_connection_response
+from ...configurations.embedding import EmbeddingConfiguration
 from ...configurations.testrail import TestRailConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 
@@ -39,22 +40,13 @@ class TestrailToolkit(BaseToolkit):
         TestrailToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         m = create_model(
             name,
-            url=(
-                str,
-                Field(
-                    description="Testrail URL",
-                    json_schema_extra={
-                        "max_length": TestrailToolkit.toolkit_max_length,
-                        "configuration": True,
-                        "configuration_title": True
-                    }
-                )
-            ),
+            name=(str, Field(description="Toolkit name", json_schema_extra={
+                'toolkit_name': True,
+                "max_length": TestrailToolkit.toolkit_max_length})),
             testrail_configuration=(Optional[TestRailConfiguration], Field(description="TestRail Configuration", json_schema_extra={'configuration_types': ['testrail']})),
             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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={'metadata':
                                                          {"label": "Testrail", "icon_url": "testrail-icon.svg",

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/utils/content_parser.py

@@ -78,9 +78,9 @@ def parse_file_content(file_name=None, file_content=None, is_capture_image: bool
 
     loader_object = loaders_map.get(extension)
     if not loader_object:
-        raise ToolException(
-            f"Not supported type ({extension}) of files entered. "
-            f"Supported types are TXT, DOCX, PDF, PPTX, XLSX and XLS only.")
+        logger.warning(f"No loader found for file extension: {extension}. File: {file_path if file_path else file_name}")
+        return ToolException(
+            "Not supported type of files entered. Supported types are TXT, DOCX, PDF, PPTX, XLSX and XLS only.")
     loader_kwargs = loader_object['kwargs']
     loader_kwargs.update({
         "file_path": file_path,

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/vector_adapters/VectorStoreAdapter.py

@@ -39,7 +39,7 @@ class VectorStoreAdapter(ABC):
         pass
 
     @abstractmethod
-    def get_code_indexed_data(self, vectorstore_wrapper) -> Dict[str, Dict[str, Any]]:
+    def get_code_indexed_data(self, vectorstore_wrapper, collection_suffix) -> Dict[str, Dict[str, Any]]:
         """Get all indexed data from vectorstore for code content"""
         pass
 
@@ -124,9 +124,10 @@ class PGVectorAdapter(VectorStoreAdapter):
         """Check if the vectorstore is a PGVector store."""
         return hasattr(vectorstore, 'session_maker') and hasattr(vectorstore, 'EmbeddingStore')
 
-    def get_indexed_data(self, vectorstore_wrapper):
-        """Get all indexed data from PGVector for non-code content"""
+    def get_indexed_data(self, vectorstore_wrapper, collection_suffix: str)-> Dict[str, Dict[str, Any]]:
+        """Get all indexed data from PGVector for non-code content per collection_suffix."""
         from sqlalchemy.orm import Session
+        from sqlalchemy import func
         from ...runtime.utils.utils import IndexerKeywords
 
         result = {}
@@ -139,6 +140,8 @@ class PGVectorAdapter(VectorStoreAdapter):
                     store.EmbeddingStore.id,
                     store.EmbeddingStore.document,
                     store.EmbeddingStore.cmetadata
+                ).filter(
+                    func.jsonb_extract_path_text(store.EmbeddingStore.cmetadata, 'collection') == collection_suffix
                 ).all()
 
             # Process the retrieved data
@@ -171,19 +174,22 @@ class PGVectorAdapter(VectorStoreAdapter):
 
         return result
 
-    def get_code_indexed_data(self, vectorstore_wrapper) -> Dict[str, Dict[str, Any]]:
-        """Get all indexed code data from PGVector."""
+    def get_code_indexed_data(self, vectorstore_wrapper, collection_suffix: str) -> Dict[str, Dict[str, Any]]:
+        """Get all indexed code data from PGVector per collection suffix."""
         from sqlalchemy.orm import Session
+        from sqlalchemy import func
 
         result = {}
         try:
             vectorstore_wrapper._log_data("Retrieving already indexed code data from PGVector vectorstore",
                            tool_name="index_code_data")
             store = vectorstore_wrapper.vectorstore
-            with Session(store.session_maker.bind) as session:
+            with (Session(store.session_maker.bind) as session):
                 docs = session.query(
                     store.EmbeddingStore.id,
                     store.EmbeddingStore.cmetadata
+                ).filter(
+                    func.jsonb_extract_path_text(store.EmbeddingStore.cmetadata, 'collection') == collection_suffix
                 ).all()
 
             for db_id, meta in docs:
@@ -319,7 +325,7 @@ class ChromaAdapter(VectorStoreAdapter):
 
         return result
 
-    def get_code_indexed_data(self, vectorstore_wrapper) -> Dict[str, Dict[str, Any]]:
+    def get_code_indexed_data(self, vectorstore_wrapper, collection_suffix) -> Dict[str, Dict[str, Any]]:
         """Get all indexed code data from Chroma."""
         result = {}
         try:

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/xray/__init__.py

@@ -8,6 +8,8 @@ from pydantic import create_model, BaseModel, Field, SecretStr
 from .api_wrapper import XrayApiWrapper
 from ..base.tool import BaseAction
 from ..utils import clean_string, get_max_toolkit_length, TOOLKIT_SPLITTER
+from ...configurations.embedding import EmbeddingConfiguration
+from ...configurations.pgvector import PgVectorConfiguration
 
 name = "xray_cloud"
 
@@ -46,14 +48,13 @@ class XrayToolkit(BaseToolkit):
             client_secret=(SecretStr, Field(description="Client secret", json_schema_extra={'secret': True})),
             limit=(Optional[int], Field(description="Limit", default=100)),
 
-            # indexer settings
-            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
-                                                          default=None,
-                                                          json_schema_extra={'secret': True})),
-
+            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']})),
 
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra':

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/zephyr_enterprise/__init__.py

@@ -5,6 +5,8 @@ from typing import List, Literal, Optional
 from .api_wrapper import ZephyrApiWrapper
 from ..base.tool import BaseAction
 from ..utils import clean_string, get_max_toolkit_length, TOOLKIT_SPLITTER
+from ...configurations.embedding import EmbeddingConfiguration
+from ...configurations.pgvector import PgVectorConfiguration
 
 name = "zephyr_enterprise"
 
@@ -37,14 +39,13 @@ class ZephyrEnterpriseToolkit(BaseToolkit):
             name,
             base_url=(str, Field(description="Zephyr Enterprise base URL", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': ZephyrEnterpriseToolkit.toolkit_max_length })),
             token=(SecretStr, Field(description="API token", json_schema_extra={'secret': True})),
-            # indexer settings
-            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
-                                                          default=None,
-                                                          json_schema_extra={'secret': True})),
-
+            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']})),
             selected_tools=(List[Literal[tuple(selected_tools)]], []),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/zephyr_essential/__init__.py

@@ -6,6 +6,8 @@ from pydantic import create_model, BaseModel, Field, SecretStr
 from .api_wrapper import ZephyrEssentialApiWrapper
 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 = "zephyr_essential"
 
@@ -37,14 +39,13 @@ class ZephyrEssentialToolkit(BaseToolkit):
             token=(str, Field(description="Bearer api token")),
             base_url=(Optional[str], Field(description="Zephyr Essential base url", default=None)),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
-            # indexer settings
-            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
-                                                          default=None,
-                                                          json_schema_extra={'secret': True})),
-
+            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__={'json_schema_extra': {'metadata': {"label": "Zephyr Essential", "icon_url": "zephyr.svg",
                             "categories": ["test management"],
                             "extra_categories": ["test automation", "test case management", "test planning"]

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk/tools/zephyr_scale/__init__.py

@@ -7,6 +7,8 @@ from pydantic import create_model, BaseModel, Field, SecretStr
 from .api_wrapper import ZephyrScaleApiWrapper
 from ..base.tool import BaseAction
 from ..utils import clean_string, get_max_toolkit_length, TOOLKIT_SPLITTER
+from ...configurations.embedding import EmbeddingConfiguration
+from ...configurations.pgvector import PgVectorConfiguration
 
 name = "zephyr_scale"
 
@@ -41,6 +43,13 @@ class ZephyrScaleToolkit(BaseToolkit):
             password=(Optional[SecretStr], Field(default=None, description="Password", json_schema_extra={'secret': True})),
             cookies=(Optional[str], Field(default=None, description="Cookies", json_schema_extra={'secret': True})),
             max_results=(int, Field(default=100, description="Results count to show")),
+            pgvector_configuration=(Optional[PgVectorConfiguration], Field(description="PgVector Configuration",
+                                                                           json_schema_extra={
+                                                                               'configuration_types': ['pgvector']})),
+            # embedder settings
+            embedding_configuration=(Optional[EmbeddingConfiguration], Field(description="Embedding configuration.",
+                                                                             json_schema_extra={'configuration_types': [
+                                                                                 'embedding']})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={

{alita_sdk-0.3.232 → alita_sdk-0.3.234}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.232
+Version: 0.3.234
 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