alita-sdk 0.3.221__tar.gz → 0.3.223__tar.gz

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.221
+Version: 0.3.223
 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-0.3.221 → alita_sdk-0.3.223}/alita_sdk/runtime/tools/artifact.py

@@ -90,7 +90,6 @@ class ArtifactWrapper(BaseVectorStoreToolApiWrapper):
                 yield Document(page_content=str(value), metadata=metadata)
         else:
             document.page_content = json.dumps(str(page_content))
-            yield document
 
     @extend_with_vector_tools
     def get_available_tools(self):

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/runtime/tools/vectorstore.py

@@ -532,10 +532,10 @@ class VectorStoreWrapper(BaseToolApiWrapper):
 
     def search_documents(self, query:str, doctype: str = 'code', 
                          filter:dict|str={}, cut_off: float=0.5,
-                         search_top:int=10, reranker:dict = {}, 
-                         full_text_search: Optional[Dict[str, Any]] = None,
-                         reranking_config: Optional[Dict[str, Dict[str, Any]]] = None,
-                         extended_search: Optional[List[str]] = None):
+                         search_top:int=10, full_text_search: Optional[Dict[str, Any]] = None,
+                         extended_search: Optional[List[str]] = None,
+                         reranker: dict = {}, reranking_config: Optional[Dict[str, Dict[str, Any]]] = None
+                         ):
         """Enhanced search documents method using JSON configurations for full-text search and reranking"""
         from alita_sdk.tools.code.loaders.codesearcher import search_format as code_format
         

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/ado/repos/__init__.py

@@ -65,6 +65,13 @@ class AzureDevOpsReposToolkit(BaseToolkit):
             connection_string = (Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
+
+            # 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"})),
             
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra': {'metadata':

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/ado/test_plan/__init__.py

@@ -33,6 +33,16 @@ class AzureDevOpsPlansToolkit(BaseToolkit):
             project=(str, Field(title="Project", description="ADO project", json_schema_extra={'configuration': True})),
             limit=(Optional[int], Field(description="ADO plans limit used for limitation of the list with results", default=5)),
             token=(SecretStr, Field(description="ADO token", json_schema_extra={'secret': True, 'configuration': True})),
+            # indexer settings
+            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
+                                                          default=None,
+                                                          json_schema_extra={'secret': True})),
+            # 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"})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra': {'metadata':
                 {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/ado/wiki/__init__.py

@@ -37,6 +37,16 @@ class AzureDevOpsWikiToolkit(BaseToolkit):
                    Field(description="ADO token",
                          json_schema_extra={'secret': True, 'configuration': True }
                          )),
+            # indexer settings
+            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
+                                                          default=None,
+                                                          json_schema_extra={'secret': True})),
+            # 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"})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/ado/work_item/__init__.py

@@ -41,6 +41,12 @@ class AzureDevOpsWorkItemsToolkit(BaseToolkit):
             connection_string = (Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
+            # 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"})),
             __config__={
                 'json_schema_extra': {
                     'metadata': {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/bitbucket/__init__.py

@@ -27,7 +27,7 @@ def get_tools(tool):
         llm=tool['settings'].get('llm', None),
         alita=tool['settings'].get('alita', None),
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=str(tool['id']),
+        collection_name=str(tool['toolkit_name']),
         doctype='code',
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
@@ -60,6 +60,10 @@ class AlitaBitbucketToolkit(BaseToolkit):
             connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                           default=None,
                                                           json_schema_extra={'secret': True})),
+
+            # 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"})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra=
             {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/confluence/__init__.py

@@ -27,7 +27,7 @@ def get_tools(tool):
         toolkit_name=tool.get('toolkit_name'),
         # indexer settings
         connection_string = tool['settings'].get('connection_string', None),
-        collection_name=str(tool['id']),
+        collection_name=str(tool['toolkit_name']),
         doctype='doc',
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
@@ -84,6 +84,11 @@ class ConfluenceToolkit(BaseToolkit):
             connection_string = (Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
+
+            # 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"})),
+
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {
                     "label": "Confluence",

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/elitea_base.py

@@ -12,6 +12,7 @@ from pydantic import BaseModel, create_model, Field, SecretStr
 from alita_sdk.runtime.langchain.interfaces.llm_processor import get_embeddings
 from .chunkers import markdown_chunker
 from .utils import TOOLKIT_SPLITTER
+from .vector_adapters.VectorStoreAdapter import VectorStoreAdapterFactory
 from ..runtime.utils.utils import IndexerKeywords
 
 logger = logging.getLogger(__name__)
@@ -59,22 +60,22 @@ BaseSearchParams = create_model(
     )),
     cut_off=(Optional[float], Field(description="Cut-off score for search results", default=0.5)),
     search_top=(Optional[int], Field(description="Number of top results to return", default=10)),
-    reranker=(Optional[dict], Field(
-        description="Reranker configuration. Can be a dictionary with reranking parameters.",
-        default={}
-    )),
     full_text_search=(Optional[Dict[str, Any]], Field(
         description="Full text search parameters. Can be a dictionary with search options.",
         default=None
     )),
-    reranking_config=(Optional[Dict[str, Dict[str, Any]]], Field(
-        description="Reranking configuration. Can be a dictionary with reranking settings.",
-        default=None
-    )),
     extended_search=(Optional[List[str]], Field(
         description="List of additional fields to include in the search results.",
         default=None
     )),
+    reranker=(Optional[dict], Field(
+        description="Reranker configuration. Can be a dictionary with reranking parameters.",
+        default={}
+    )),
+    reranking_config=(Optional[Dict[str, Dict[str, Any]]], Field(
+        description="Reranking configuration. Can be a dictionary with reranking settings.",
+        default=None
+    )),
 )
 
 BaseStepbackSearchParams = create_model(
@@ -111,7 +112,7 @@ BaseStepbackSearchParams = create_model(
 BaseIndexDataParams = create_model(
     "indexData",
     __base__=BaseIndexParams,
-    progress_step=(Optional[int], Field(default=None, ge=0, le=100,
+    progress_step=(Optional[int], Field(default=10, ge=0, le=100,
                          description="Optional step size for progress reporting during indexing")),
     clean_index=(Optional[bool], Field(default=False,
                        description="Optional flag to enforce clean existing index before indexing new data")),
@@ -219,6 +220,10 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
     embedding_model_params: Optional[Dict[str, Any]] = {"model_name": "sentence-transformers/all-MiniLM-L6-v2"}
     vectorstore_type: Optional[str] = "PGVector"
 
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self._adapter = VectorStoreAdapterFactory.create_adapter(self.vectorstore_type)
+
     def _index_tool_params(self, **kwargs) -> dict[str, tuple[type, Field]]:
         """
         Returns a list of fields for index_data args schema.
@@ -329,36 +334,24 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
 
     # TODO: init store once and re-use the instance
     def _init_vector_store(self, collection_suffix: str = "", embeddings: Optional[Any] = None):
-        """ Initializes the vector store wrapper with the provided parameters."""
+        """Initializes the vector store wrapper with the provided parameters."""
         try:
             from alita_sdk.runtime.tools.vectorstore import VectorStoreWrapper
         except ImportError:
             from alita_sdk.runtime.tools.vectorstore import VectorStoreWrapper
-        
+
         # Validate collection_suffix length
         if collection_suffix and len(collection_suffix.strip()) > 7:
             raise ToolException("collection_suffix must be 7 characters or less")
-        
+
         # Create collection name with suffix if provided
         collection_name = str(self.collection_name)
         if collection_suffix and collection_suffix.strip():
             collection_name = f"{self.collection_name}_{collection_suffix.strip()}"
-        
-        if self.vectorstore_type == 'PGVector':
-            vectorstore_params = {
-                "use_jsonb": True,
-                "collection_name": collection_name,
-                "create_extension": True,
-                "alita_sdk_options": {
-                    "target_schema": collection_name,
-                },
-                "connection_string": self.connection_string.get_secret_value()
-            }
-        elif self.vectorstore_type == 'Chroma':
-            vectorstore_params = {
-                "collection_name": collection_name,
-                "persist_directory": "./indexer_db"
-            }
+
+        # Get database-specific parameters using adapter
+        connection_string = self.connection_string.get_secret_value() if self.connection_string else None
+        vectorstore_params = self._adapter.get_vectorstore_params(collection_name, connection_string)
 
         return VectorStoreWrapper(
             llm=self.llm,
@@ -371,36 +364,17 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
         )
 
     def remove_index(self, collection_suffix: str = ""):
-        """
-            Cleans the indexed data in the collection
-        """
-
-        self._init_vector_store(collection_suffix)._remove_collection()
+        """Cleans the indexed data in the collection."""
+        vectorstore_wrapper = self._init_vector_store(collection_suffix)
+        collection_name = f"{self.collection_name}_{collection_suffix}" if collection_suffix else str(self.collection_name)
+        self._adapter.remove_collection(vectorstore_wrapper, collection_name)
+        return (f"Collection '{collection_name}' has been removed from the vector store.\n"
+                f"Available collections: {self.list_collections()}")
 
     def list_collections(self):
-        """
-            Lists all collections in the vector store
-        """
-        if self.vectorstore_type.lower() == 'PGVector'.lower():
-            from sqlalchemy import text
-            from sqlalchemy.orm import Session
-
-            # schema_name = self.vectorstore.collection_name
-            with Session(self._init_vector_store().vectorstore.session_maker.bind) as session:
-                get_collections = text("""
-                    SELECT table_schema
-                    FROM information_schema.columns
-                    WHERE udt_name = 'vector';
-                """)
-
-                # Execute the raw SQL query
-                result = session.execute(get_collections)
-
-                # Fetch all rows from the result
-                docs = result.fetchall()
-            return str(docs)
-        vector_client = self._init_vector_store().vectoradapter.vectorstore._client
-        return ','.join([collection.name for collection in vector_client.list_collections()])
+        """Lists all collections in the vector store."""
+        vectorstore_wrapper = self._init_vector_store()
+        return self._adapter.list_collections(vectorstore_wrapper)
 
     def search_index(self,
                      query: str,

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/figma/__init__.py

@@ -22,7 +22,7 @@ def get_tools(tool):
             # indexer settings
             llm=tool['settings'].get('llm', None),
             connection_string = tool['settings'].get('connection_string', None),
-            collection_name=str(tool['id']),
+            collection_name=str(tool['toolkit_name']),
             doctype='doc',
             embedding_model="HuggingFaceEmbeddings",
             embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
@@ -57,6 +57,10 @@ class FigmaToolkit(BaseToolkit):
             connection_string = (Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
+
+            # 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"})),
             __config__=ConfigDict(
                 json_schema_extra={
                      "metadata": {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/github/__init__.py

@@ -25,7 +25,7 @@ def _get_toolkit(tool) -> BaseToolkit:
         llm=tool['settings'].get('llm', None),
         alita=tool['settings'].get('alita', None),
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=str(tool['id']),
+        collection_name=str(tool['toolkit_name']),
         doctype='code',
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
@@ -96,6 +96,10 @@ class AlitaGitHubToolkit(BaseToolkit):
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
             
+            # 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"})),
+
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools}))
         )
 
@@ -123,4 +127,3 @@ class AlitaGitHubToolkit(BaseToolkit):
 
     def get_tools(self):
         return self.tools
-

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/gitlab/__init__.py

@@ -7,7 +7,6 @@ from pydantic import create_model, BaseModel, ConfigDict, SecretStr
 from pydantic.fields import Field
 
 from .api_wrapper import GitLabAPIWrapper
-# from .tools import __all__
 from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
 
 name = "gitlab"
@@ -24,7 +23,7 @@ def get_tools(tool):
         llm=tool['settings'].get('llm', None),
         alita=tool['settings'].get('alita', None),
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        collection_name=str(tool['toolkit_name']),
         doctype='code',
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
@@ -51,6 +50,10 @@ class AlitaGitlabToolkit(BaseToolkit):
             connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                           default=None,
                                                           json_schema_extra={'secret': True})),
+
+            # 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"})),
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/jira/__init__.py

@@ -25,7 +25,7 @@ def get_tools(tool):
         llm=tool['settings'].get('llm', None),
         alita=tool['settings'].get('alita', None),
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        collection_name=str(tool['toolkit_name']),
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector",
@@ -81,6 +81,16 @@ class JiraToolkit(BaseToolkit):
             )),
             verify_ssl=(bool, Field(description="Verify SSL", default=True)),
             additional_fields=(Optional[str], Field(description="Additional fields", default="")),
+
+            # indexer settings
+            connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
+                                                          default=None,
+                                                          json_schema_extra={'secret': True})),
+
+            # 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"})),
+
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/sharepoint/__init__.py

@@ -18,7 +18,7 @@ def get_tools(tool):
         llm=tool['settings'].get('llm'),
         # indexer settings
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        collection_name=str(tool['toolkit_name']),
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector")
@@ -43,6 +43,10 @@ class SharepointToolkit(BaseToolkit):
             connection_string = (Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                             default=None,
                                                             json_schema_extra={'secret': True})),
+
+            # 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"})),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {
                     "label": "Sharepoint", "icon_url": "sharepoint.svg",

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/sharepoint/api_wrapper.py

@@ -172,7 +172,6 @@ class SharepointApiWrapper(BaseVectorStoreToolApiWrapper):
                 yield Document(page_content=str(content), metadata=new_metadata)
         else:
             document.page_content = str(doc_content)
-            yield document
 
     @extend_with_vector_tools
     def get_available_tools(self):

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/testrail/__init__.py

@@ -55,6 +55,10 @@ class TestrailToolkit(BaseToolkit):
             connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                           default=None,
                                                           json_schema_extra={'secret': True})),
+
+            # 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"})),
             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-0.3.223/alita_sdk/tools/vector_adapters/VectorStoreAdapter.py

@@ -0,0 +1,91 @@
+from abc import ABC, abstractmethod
+from typing import Any, Dict, Optional
+
+
+class VectorStoreAdapter(ABC):
+    """Abstract base class for vector store adapters."""
+
+    @abstractmethod
+    def get_vectorstore_params(self, collection_name: str, connection_string: Optional[str] = None) -> Dict[str, Any]:
+        """Get vector store specific parameters."""
+        pass
+
+    @abstractmethod
+    def list_collections(self, vectorstore_wrapper) -> str:
+        """List all collections in the vector store."""
+        pass
+
+    @abstractmethod
+    def remove_collection(self, vectorstore_wrapper, collection_name: str):
+        """Remove a collection from the vector store."""
+        pass
+
+
+class PGVectorAdapter(VectorStoreAdapter):
+    """Adapter for PGVector database operations."""
+
+    def get_vectorstore_params(self, collection_name: str, connection_string: Optional[str] = None) -> Dict[str, Any]:
+        return {
+            "use_jsonb": True,
+            "collection_name": collection_name,
+            "create_extension": True,
+            "alita_sdk_options": {
+                "target_schema": collection_name,
+            },
+            "connection_string": connection_string
+        }
+
+    def list_collections(self, vectorstore_wrapper) -> str:
+        from sqlalchemy import text
+        from sqlalchemy.orm import Session
+
+        with Session(vectorstore_wrapper.vectorstore.session_maker.bind) as session:
+            get_collections = text("""
+                SELECT table_schema
+                FROM information_schema.columns
+                WHERE udt_name = 'vector';
+            """)
+            result = session.execute(get_collections)
+            docs = result.fetchall()
+        return str(docs)
+
+    def remove_collection(self, vectorstore_wrapper, collection_name: str):
+        vectorstore_wrapper._remove_collection()
+
+
+class ChromaAdapter(VectorStoreAdapter):
+    """Adapter for Chroma database operations."""
+
+    def get_vectorstore_params(self, collection_name: str, connection_string: Optional[str] = None) -> Dict[str, Any]:
+        return {
+            "collection_name": collection_name,
+            "persist_directory": "./indexer_db"
+        }
+
+    def list_collections(self, vectorstore_wrapper) -> str:
+        vector_client = vectorstore_wrapper.vectoradapter.vectorstore._client
+        return ','.join([collection.name for collection in vector_client.list_collections()])
+
+    def remove_collection(self, vectorstore_wrapper, collection_name: str):
+        vectorstore_wrapper.vectoradapter.vectorstore.delete_collection()
+
+
+class VectorStoreAdapterFactory:
+    """Factory for creating vector store adapters."""
+
+    _adapters = {
+        'PGVector': PGVectorAdapter,
+        'Chroma': ChromaAdapter,
+    }
+
+    @classmethod
+    def create_adapter(cls, vectorstore_type: str) -> VectorStoreAdapter:
+        adapter_class = cls._adapters.get(vectorstore_type)
+        if not adapter_class:
+            raise ValueError(f"Unsupported vectorstore type: {vectorstore_type}")
+        return adapter_class()
+
+    @classmethod
+    def register_adapter(cls, vectorstore_type: str, adapter_class: type):
+        """Register a new adapter for a vector store type."""
+        cls._adapters[vectorstore_type] = adapter_class

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/xray/__init__.py

@@ -24,7 +24,7 @@ def get_tools(tool):
 
         # indexer settings
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        collection_name=str(tool['toolkit_name']),
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector"
@@ -45,6 +45,16 @@ class XrayToolkit(BaseToolkit):
             client_id=(str, Field(description="Client ID")),
             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})),
+
+            # 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"})),
+
             selected_tools=(List[Literal[tuple(selected_tools)]], Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __config__={'json_schema_extra':
                             {

{alita_sdk-0.3.221 → alita_sdk-0.3.223}/alita_sdk/tools/zephyr_enterprise/__init__.py

@@ -18,7 +18,7 @@ def get_tools(tool):
 
         # indexer settings
         connection_string=tool['settings'].get('connection_string', None),
-        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        collection_name=str(tool['toolkit_name']),
         embedding_model="HuggingFaceEmbeddings",
         embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
         vectorstore_type="PGVector"
@@ -41,6 +41,10 @@ class ZephyrEnterpriseToolkit(BaseToolkit):
             connection_string=(Optional[SecretStr], Field(description="Connection string for vectorstore",
                                                           default=None,
                                                           json_schema_extra={'secret': True})),
+
+            # 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"})),
             selected_tools=(List[Literal[tuple(selected_tools)]], []),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {
@@ -71,4 +75,3 @@ class ZephyrEnterpriseToolkit(BaseToolkit):
 
     def get_tools(self) -> List[BaseTool]:
         return self.tools
-