alita-sdk 0.3.392__tar.gz → 0.3.393__tar.gz

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.392
+Version: 0.3.393
 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 <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/alita_sdk/runtime/langchain/langraph_agent.py

@@ -348,8 +348,8 @@ class StateModifierNode(Runnable):
         return result
 
 
-
-def prepare_output_schema(lg_builder, memory, store, debug=False, interrupt_before=None, interrupt_after=None, state_class=None, output_variables=None):
+def prepare_output_schema(lg_builder, memory, store, debug=False, interrupt_before=None, interrupt_after=None,
+                          state_class=None, output_variables=None):
     # prepare output channels
     if interrupt_after is None:
         interrupt_after = []
@@ -466,7 +466,7 @@ def create_graph(
                         elif node_type == 'agent':
                             input_params = node.get('input', ['messages'])
                             input_mapping = node.get('input_mapping',
-                                                       {'messages': {'type': 'variable', 'value': 'messages'}})
+                                                     {'messages': {'type': 'variable', 'value': 'messages'}})
                             lg_builder.add_node(node_id, FunctionTool(
                                 client=client, tool=tool,
                                 name=node_id, return_type='str',
@@ -481,7 +481,8 @@ def create_graph(
                             # wrap with mappings
                             pipeline_name = node.get('tool', None)
                             if not pipeline_name:
-                                raise ValueError("Subgraph must have a 'tool' node: add required tool to the subgraph node")
+                                raise ValueError(
+                                    "Subgraph must have a 'tool' node: add required tool to the subgraph node")
                             node_fn = SubgraphRunnable(
                                 inner=tool.graph,
                                 name=pipeline_name,
@@ -520,7 +521,8 @@ def create_graph(
                             loop_toolkit_name = node.get('loop_toolkit_name')
                             loop_tool_name = node.get('loop_tool')
                             if (loop_toolkit_name and loop_tool_name) or loop_tool_name:
-                                loop_tool_name = f"{clean_string(loop_toolkit_name)}{TOOLKIT_SPLITTER}{loop_tool_name}" if loop_toolkit_name else clean_string(loop_tool_name)
+                                loop_tool_name = f"{clean_string(loop_toolkit_name)}{TOOLKIT_SPLITTER}{loop_tool_name}" if loop_toolkit_name else clean_string(
+                                    loop_tool_name)
                                 for t in tools:
                                     if t.name == loop_tool_name:
                                         logger.debug(f"Loop tool discovered: {t}")
@@ -555,7 +557,8 @@ def create_graph(
                         break
             elif node_type == 'code':
                 from ..tools.sandbox import create_sandbox_tool
-                sandbox_tool = create_sandbox_tool(stateful=False, allow_net=True, alita_client=kwargs.get('alita_client', None))
+                sandbox_tool = create_sandbox_tool(stateful=False, allow_net=True,
+                                                   alita_client=kwargs.get('alita_client', None))
                 code_data = node.get('code', {'type': 'fixed', 'value': "return 'Code block is empty'"})
                 lg_builder.add_node(node_id, FunctionTool(
                     tool=sandbox_tool, name=node['id'], return_type='dict',
@@ -777,7 +780,13 @@ class LangGraphAgentRunnable(CompiledStateGraph):
             # Convert chat history dict messages to LangChain message objects
             chat_history = input.pop('chat_history')
             input['messages'] = [convert_dict_to_message(msg) for msg in chat_history]
-        
+
+        # handler for LLM node: if no input (Chat perspective), then take last human message
+        if not input.get('input'):
+            if input.get('messages'):
+                input['input'] = [next((msg for msg in reversed(input['messages']) if isinstance(msg, HumanMessage)),
+                                          None)]
+
         # Append current input to existing messages instead of overwriting
         if input.get('input'):
             if isinstance(input['input'], str):
@@ -801,7 +810,8 @@ class LangGraphAgentRunnable(CompiledStateGraph):
         else:
             result = super().invoke(input, config=config, *args, **kwargs)
         try:
-            output = next((msg.content for msg in reversed(result['messages']) if not isinstance(msg, HumanMessage)), result['messages'][-1].content)
+            output = next((msg.content for msg in reversed(result['messages']) if not isinstance(msg, HumanMessage)),
+                          result['messages'][-1].content)
         except:
             output = list(result.values())[-1]
         config_state = self.get_state(config)
@@ -809,8 +819,6 @@ class LangGraphAgentRunnable(CompiledStateGraph):
         if is_execution_finished:
             thread_id = None
 
-
-
         result_with_state = {
             "output": output,
             "thread_id": thread_id,

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/alita_sdk/tools/base_indexer_toolkit.py

@@ -160,6 +160,8 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
             if clean_index:
                 self._clean_index(index_name)
             #
+            self.index_meta_init(index_name, kwargs)
+            #
             self._log_tool_event(f"Indexing data into collection with suffix '{index_name}'. It can take some time...")
             self._log_tool_event(f"Loading the documents to index...{kwargs}")
             documents = self._base_loader(**kwargs)
@@ -454,6 +456,29 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
             reranking_config=reranking_config, 
             extended_search=extended_search
         )
+    
+    def index_meta_init(self, index_name: str, index_configuration: dict[str, Any]):
+        index_meta = super().get_index_meta(index_name)
+        if not index_meta:
+            self._log_tool_event(
+                f"There is no existing index_meta for collection '{index_name}'. Initializing it.",
+                tool_name="index_data"
+            )
+            from ..runtime.langchain.interfaces.llm_processor import add_documents
+            created_on = time.time()
+            metadata = {
+                "collection": index_name,
+                "type": IndexerKeywords.INDEX_META_TYPE.value,
+                "indexed": 0,
+                "state": IndexerKeywords.INDEX_META_IN_PROGRESS.value,
+                "index_configuration": index_configuration,
+                "created_on": created_on,
+                "updated_on": created_on,
+                "history": "[]",
+                "task_id": None,
+            }
+            index_meta_doc = Document(page_content=f"{IndexerKeywords.INDEX_META_TYPE.value}_{index_name}", metadata=metadata)
+            add_documents(vectorstore=self.vectorstore, documents=[index_meta_doc])
 
     def index_meta_update(self, index_name: str, state: str, result: int):
         index_meta_raw = super().get_index_meta(index_name)

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/alita_sdk/tools/confluence/loader.py

@@ -3,6 +3,7 @@ from typing import Optional, List
 from logging import getLogger
 
 import requests
+from langchain_core.documents import Document
 
 logger = getLogger(__name__)
 from PIL import Image
@@ -193,6 +194,15 @@ class AlitaConfluenceLoader(ConfluenceLoader):
         else:
             return super().process_image(link, ocr_languages)
 
+    def process_page(self, page: dict, include_attachments: bool, include_comments: bool, include_labels: bool,
+                     content_format: ContentFormat, ocr_languages: Optional[str] = None,
+                     keep_markdown_format: Optional[bool] = False, keep_newlines: bool = False) -> Document:
+        if not page.get("title"):
+            # if 'include_restricted_content' set to True, draft pages are loaded and can have no title
+            page["title"] = "Untitled"
+        return super().process_page(page, include_attachments, include_comments, include_labels, content_format,
+                                    ocr_languages, keep_markdown_format, keep_newlines)
+
     # TODO review usage
     # def process_svg(
     #         self,

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/alita_sdk/tools/vector_adapters/VectorStoreAdapter.py

@@ -136,7 +136,15 @@ class PGVectorAdapter(VectorStoreAdapter):
         """Clean the vectorstore collection by deleting all indexed data."""
         # This logic deletes all data from the vectorstore collection without removal of collection.
         # Collection itself remains available for future indexing.
-        vectorstore_wrapper.vectorstore.delete(ids=self.get_indexed_ids(vectorstore_wrapper, index_name))
+        from sqlalchemy.orm import Session
+        from sqlalchemy import func
+
+        store = vectorstore_wrapper.vectorstore
+        with Session(store.session_maker.bind) as session:
+            session.query(store.EmbeddingStore).filter(
+                func.jsonb_extract_path_text(store.EmbeddingStore.cmetadata, 'collection') == index_name
+            ).delete(synchronize_session=False)
+            session.commit()
 
     def is_vectorstore_type(self, vectorstore) -> bool:
         """Check if the vectorstore is a PGVector store."""

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.392
+Version: 0.3.393
 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 <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.392 → alita_sdk-0.3.393}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.392"
+version = "0.3.393"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"