alita-sdk 0.3.216__tar.gz → 0.3.218__tar.gz

{alita_sdk-0.3.216 → alita_sdk-0.3.218}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.216
+Version: 0.3.218
 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-0.3.216 → alita_sdk-0.3.218}/alita_sdk/runtime/tools/vectorstore.py

@@ -196,35 +196,95 @@ class VectorStoreWrapper(BaseToolApiWrapper):
             f"Cleaning collection '{self.dataset}'",
             tool_name="_clean_collection"
         )
-        data = self.vectoradapter.vectorstore.get(include=['metadatas'])
-        if data['ids']:
-            self.vectoradapter.vectorstore.delete(ids=data['ids'])
+        # This logic deletes the entire collection
+        # Works for PGVector and Chroma
+        self.vectoradapter.vectorstore.delete_collection()
+        # This logic deletes all data from the vectorstore collection without removal of collection.
+        # data = self.vectoradapter.vectorstore.get(include=['metadatas'])
+        # if data['ids']:
+        #     self.vectoradapter.vectorstore.delete(ids=data['ids'])
         self._log_data(
             f"Collection '{self.dataset}' has been cleaned. ",
             tool_name="_clean_collection"
         )
 
+    # TODO: refactor to use common method for different vectorstores in a separate vectorstore wrappers
     def _get_indexed_data(self, store):
         """ Get all indexed data from vectorstore for non-code content """
 
-        # get already indexed data
+        # Check if this is a PGVector store
+        if hasattr(store, 'session_maker') and hasattr(store, 'EmbeddingStore'):
+            return self._get_pgvector_indexed_data(store)
+        else:
+            # Fall back to original Chroma implementation
+            return self._get_chroma_indexed_data(store)
+
+    def _get_pgvector_indexed_data(self, store):
+        """ Get all indexed data from PGVector for non-code content """
+        from sqlalchemy.orm import Session
+
         result = {}
         try:
-            self._log_data("Retrieving already indexed data from vectorstore",
+            self._log_data("Retrieving already indexed data from PGVector vectorstore",
+                           tool_name="index_documents")
+
+            with Session(store.session_maker.bind) as session:
+                docs = session.query(
+                    store.EmbeddingStore.id,
+                    store.EmbeddingStore.document,
+                    store.EmbeddingStore.cmetadata
+                ).all()
+
+            # Process the retrieved data
+            for doc in docs:
+                db_id = doc.id
+                meta = doc.cmetadata or {}
+
+                # Get document id from metadata
+                doc_id = str(meta.get('id', db_id))
+                dependent_docs = meta.get(IndexerKeywords.DEPENDENT_DOCS.value, [])
+                if dependent_docs:
+                    dependent_docs = [d.strip() for d in dependent_docs.split(';') if d.strip()]
+                parent_id = meta.get(IndexerKeywords.PARENT.value, -1)
+
+                chunk_id = meta.get('chunk_id')
+                if doc_id in result and chunk_id:
+                    # If document with the same id already saved, add db_id for current one as chunk
+                    result[doc_id]['all_chunks'].append(db_id)
+                else:
+                    result[doc_id] = {
+                        'metadata': meta,
+                        'id': db_id,
+                        'all_chunks': [db_id],
+                        IndexerKeywords.DEPENDENT_DOCS.value: dependent_docs,
+                        IndexerKeywords.PARENT.value: parent_id
+                    }
+
+        except Exception as e:
+            logger.error(f"Failed to get indexed data from PGVector: {str(e)}. Continuing with empty index.")
+
+        return result
+
+    def _get_chroma_indexed_data(self, store):
+        """ Get all indexed data from Chroma for non-code content """
+        result = {}
+        try:
+            self._log_data("Retrieving already indexed data from Chroma vectorstore",
                            tool_name="index_documents")
             data = store.get(include=['metadatas'])
-            # re-structure data to be more usable
+
+            # Re-structure data to be more usable
             for meta, db_id in zip(data['metadatas'], data['ids']):
-                # get document id from metadata
+                # Get document id from metadata
                 doc_id = str(meta['id'])
                 dependent_docs = meta.get(IndexerKeywords.DEPENDENT_DOCS.value, [])
                 if dependent_docs:
                     dependent_docs = [d.strip() for d in dependent_docs.split(';') if d.strip()]
                 parent_id = meta.get(IndexerKeywords.PARENT.value, -1)
-                #
+
                 chunk_id = meta.get('chunk_id')
                 if doc_id in result and chunk_id:
-                    # if document with the same id already saved, add db_id fof current one as chunk
+                    # If document with the same id already saved, add db_id for current one as chunk
                     result[doc_id]['all_chunks'].append(db_id)
                 else:
                     result[doc_id] = {
@@ -235,7 +295,8 @@ class VectorStoreWrapper(BaseToolApiWrapper):
                         IndexerKeywords.PARENT.value: parent_id
                     }
         except Exception as e:
-            logger.error(f"Failed to get indexed data from vectorstore: {str(e)}. Continuing with empty index.")
+            logger.error(f"Failed to get indexed data from Chroma: {str(e)}. Continuing with empty index.")
+
         return result
 
     def _get_code_indexed_data(self, store) -> Dict[str, Dict[str, Any]]:

{alita_sdk-0.3.216 → alita_sdk-0.3.218}/alita_sdk/tools/elitea_base.py

@@ -327,6 +327,7 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
                             yield processed_doc
 
 
+    # 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."""
         try:
@@ -380,7 +381,8 @@ class BaseVectorStoreToolApiWrapper(BaseToolApiWrapper):
         """
             Lists all collections in the vector store
         """
-        return ','.join([collection.name for collection in self.vectoradapter.vectorstore._client.list_collections()])
+        vector_client = self._init_vector_store().vectoradapter.vectorstore._client
+        return ','.join([collection.name for collection in vector_client.list_collections()])
 
     def search_index(self,
                      query: str,

{alita_sdk-0.3.216 → alita_sdk-0.3.218}/alita_sdk/tools/zephyr_enterprise/__init__.py

@@ -13,7 +13,15 @@ def get_tools(tool):
         selected_tools=tool['settings'].get('selected_tools', []),
         base_url=tool['settings']['base_url'],
         token=tool['settings']['token'],
-        toolkit_name=tool.get('toolkit_name')
+        toolkit_name=tool.get('toolkit_name'),
+        llm=tool['settings'].get('llm', None),
+
+        # indexer settings
+        connection_string=tool['settings'].get('connection_string', None),
+        collection_name=f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        embedding_model="HuggingFaceEmbeddings",
+        embedding_model_params={"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        vectorstore_type="PGVector"
     ).get_tools()
 
 class ZephyrEnterpriseToolkit(BaseToolkit):
@@ -29,6 +37,10 @@ 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})),
             selected_tools=(List[Literal[tuple(selected_tools)]], []),
             __config__=ConfigDict(json_schema_extra={
                 'metadata': {

{alita_sdk-0.3.216 → alita_sdk-0.3.218}/alita_sdk/tools/zephyr_essential/__init__.py

@@ -13,7 +13,15 @@ def get_tools(tool):
     return ZephyrEssentialToolkit().get_toolkit(
         selected_tools=tool['settings'].get('selected_tools', []),
         token=tool['settings']["token"],
-        toolkit_name=tool.get('toolkit_name')
+        toolkit_name=tool.get('toolkit_name'),
+        llm = tool['settings'].get('llm', None),
+
+        # indexer settings
+        connection_string = tool['settings'].get('connection_string', None),
+        collection_name = f"{tool.get('toolkit_name')}_{str(tool['id'])}",
+        embedding_model = "HuggingFaceEmbeddings",
+        embedding_model_params = {"model_name": "sentence-transformers/all-MiniLM-L6-v2"},
+        vectorstore_type = "PGVector"
     ).get_tools()
 
 class ZephyrEssentialToolkit(BaseToolkit):
@@ -29,6 +37,10 @@ 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})),
             __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-0.3.216 → alita_sdk-0.3.218}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.216
+Version: 0.3.218
 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-0.3.216 → alita_sdk-0.3.218}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.216"
+version = "0.3.218"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"