alita-sdk 0.3.379__tar.gz → 0.3.381__tar.gz

{alita_sdk-0.3.379 → alita_sdk-0.3.381}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.379
+Version: 0.3.381
 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-0.3.379 → alita_sdk-0.3.381}/alita_sdk/runtime/tools/graph.py

@@ -47,8 +47,8 @@ def formulate_query(kwargs):
 
 
 class GraphTool(BaseTool):
-    name: str
-    description: str
+    name: str = 'GraphTool'
+    description: str = 'Graph tool for tools'
     graph: CompiledStateGraph
     args_schema: Type[BaseModel] = graphToolSchema
     return_type: str = "str"
@@ -65,10 +65,16 @@ class GraphTool(BaseTool):
         all_kwargs = {**kwargs, **extras, **schema_values}
         if config is None:
             config = {}
-        return self._run(*config, **all_kwargs)
+        # Pass the config to the _run empty or the one passed from the parent executor.
+        return self._run(config, **all_kwargs)
 
     def _run(self, *args, **kwargs):
-        response = self.graph.invoke(formulate_query(kwargs))
+        config = None
+        # From invoke method we are passing only 1 arg so it is safe to do this condition and config assignment.
+        # Default to None is safe because it will be checked also on the langchain side.
+        if args:
+            config = args[0]
+        response = self.graph.invoke(formulate_query(kwargs), config=config)
         if self.return_type == "str":
             return response["output"]
         else:

{alita_sdk-0.3.379 → alita_sdk-0.3.381}/alita_sdk/runtime/tools/llm.py

@@ -177,7 +177,9 @@ class LLMNode(BaseTool):
                             if tool_to_execute:
                                 try:
                                     logger.info(f"Executing tool '{tool_name}' with args: {tool_args}")
-                                    tool_result = tool_to_execute.invoke(tool_args)
+                                    # Pass the underlying config to the tool execution invoke method
+                                    # since it may be another agent, graph, etc. to see it properly in thinking steps
+                                    tool_result = tool_to_execute.invoke(tool_args, config=config)
 
                                     # Create tool message with result - preserve structured content
                                     from langchain_core.messages import ToolMessage

{alita_sdk-0.3.379 → alita_sdk-0.3.381}/alita_sdk/tools/base_indexer_toolkit.py

@@ -161,8 +161,6 @@ 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)
@@ -455,39 +453,6 @@ 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_raw = super().get_index_meta(index_name)
-        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": "[]",
-        }
-        index_meta_ids = None
-        #
-        if index_meta_raw:
-            history_raw = index_meta_raw.get("metadata", {}).get("history", "[]")
-            if isinstance(history_raw, str) and history_raw.strip():
-                try:
-                    history = json.loads(history_raw)
-                except (json.JSONDecodeError, TypeError):
-                    history = []
-            else:
-                history = []
-            new_history_item = {k: v for k, v in index_meta_raw.get("metadata", {}).items() if k != "history"}
-            history.append(new_history_item)
-            metadata["history"] = json.dumps(history)
-            index_meta_ids = [index_meta_raw.get("id")]
-        #
-        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], ids=index_meta_ids)
 
     def index_meta_update(self, index_name: str, state: str, result: int):
         index_meta_raw = super().get_index_meta(index_name)

{alita_sdk-0.3.379 → alita_sdk-0.3.381}/alita_sdk/tools/confluence/api_wrapper.py

@@ -7,12 +7,14 @@ from json import JSONDecodeError
 from typing import Optional, List, Any, Dict, Callable, Generator, Literal
 
 import requests
+from atlassian.errors import ApiError
 from langchain_community.document_loaders.confluence import ContentFormat
 from langchain_core.documents import Document
 from langchain_core.messages import HumanMessage
 from langchain_core.tools import ToolException
 from markdownify import markdownify
 from pydantic import Field, PrivateAttr, model_validator, create_model, SecretStr
+from requests import HTTPError
 from tenacity import retry, stop_after_attempt, wait_exponential, before_sleep_log
 
 from alita_sdk.tools.non_code_indexer_toolkit import NonCodeIndexerToolkit
@@ -194,6 +196,7 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
     keep_markdown_format: Optional[bool] = True
     ocr_languages: Optional[str] = None
     keep_newlines: Optional[bool] = True
+    _errors: Optional[list[str]] = None
     _image_cache: ImageDescriptionCache = PrivateAttr(default_factory=ImageDescriptionCache)
 
     @model_validator(mode='before')
@@ -498,7 +501,9 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
         restrictions = self.client.get_all_restrictions_for_content(page["id"])
 
         return (
-                page["status"] == "current"
+                (page["status"] == "current"
+                # allow user to see archived content if needed
+                 or page["status"] == "archived")
                 and not restrictions["read"]["restrictions"]["user"]["results"]
                 and not restrictions["read"]["restrictions"]["group"]["results"]
         )
@@ -518,18 +523,34 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
                 ),
                 before_sleep=before_sleep_log(logger, logging.WARNING),
             )(self.client.get_page_by_id)
-            page = get_page(
-                page_id=page_id, expand=f"{self.content_format.value},version"
-            )
+            try:
+                page = get_page(
+                    page_id=page_id, expand=f"{self.content_format.value},version"
+                )
+            except (ApiError, HTTPError) as e:
+                logger.error(f"Error fetching page with ID {page_id}: {e}")
+                page_content_temp = f"Confluence API Error: cannot fetch the page with ID {page_id}: {e}"
+                # store errors
+                if self._errors is None:
+                    self._errors = []
+                self._errors.append(page_content_temp)
+                return Document(page_content=page_content_temp,
+                                metadata={})
             if not self.include_restricted_content and not self.is_public_page(page):
                 continue
             yield self.process_page(page, skip_images)
 
+    def _log_errors(self):
+        """ Log errors encountered during toolkit execution. """
+        if self._errors:
+            logger.info(f"Errors encountered during toolkit execution: {self._errors}")
+
     def read_page_by_id(self, page_id: str, skip_images: bool = False):
         """Reads a page by its id in the Confluence space. If id is not available, but there is a title - use get_page_id first."""
         result = list(self.get_pages_by_id([page_id], skip_images))
         if not result:
-            "Page not found"
+            return f"Pages not found. Errors: {self._errors}" if self._errors \
+                else "Pages not found or you do not have access to them."
         return result[0].page_content
         # return self._strip_base64_images(result[0].page_content) if skip_images else result[0].page_content
 

{alita_sdk-0.3.379 → alita_sdk-0.3.381}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.379
+Version: 0.3.381
 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-0.3.379 → alita_sdk-0.3.381}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.379"
+version = "0.3.381"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"