alita-sdk 0.3.257__py3-none-any.whl → 0.3.562__py3-none-any.whl

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
@@ -47,7 +48,8 @@ class AlitaConfluenceLoader(ConfluenceLoader):
                 del kwargs[key]
             except:
                 pass
-        self.base_url = kwargs.get('url')
+        # utilize adjusted URL from Confluence instance for base_url
+        self.base_url = confluence_client.url
         self.space_key = kwargs.get('space_key')
         self.page_ids = kwargs.get('page_ids')
         self.label = kwargs.get('label')
@@ -107,7 +109,8 @@ class AlitaConfluenceLoader(ConfluenceLoader):
         texts = []
         for attachment in attachments:
             media_type = attachment["metadata"]["mediaType"]
-            absolute_url = self.base_url + attachment["_links"]["download"]
+            # utilize adjusted URL from Confluence instance for attachment download URL
+            absolute_url = self.confluence.url + attachment["_links"]["download"]
             title = attachment["title"]
             try:
                 if media_type == "application/pdf":
@@ -193,6 +196,15 @@ 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/tools/custom_open_api/__init__.py

@@ -5,7 +5,7 @@ from pydantic import create_model, BaseModel, ConfigDict, Field
 
 from .api_wrapper import OpenApiWrapper
 from ..base.tool import BaseAction
-from ..utils import clean_string, TOOLKIT_SPLITTER
+from ..utils import clean_string
 
 name = "openapi"
 
@@ -43,15 +43,21 @@ class OpenApiToolkit(BaseToolkit):
         openapi_api_wrapper = OpenApiWrapper(**kwargs)
         available_tools = openapi_api_wrapper.get_available_tools()
         tools = []
-        prefix = clean_string(toolkit_name + TOOLKIT_SPLITTER) if toolkit_name else ''
+        # Use clean toolkit name for context (max 1000 chars in description)
+        toolkit_context = f" [Toolkit: {clean_string(toolkit_name)}]" if toolkit_name else ''
         for tool in available_tools:
             if selected_tools and tool["name"] not in selected_tools:
                 continue
+            # Add toolkit context to description with character limit
+            description = tool["description"]
+            if toolkit_context and len(description + toolkit_context) <= 1000:
+                description = description + toolkit_context
             tools.append(BaseAction(
                 api_wrapper=openapi_api_wrapper,
-                name=prefix + tool["name"],
-                description=tool["description"],
-                args_schema=tool["args_schema"]
+                name=tool["name"],
+                description=description,
+                args_schema=tool["args_schema"],
+                metadata={"toolkit_name": toolkit_name} if toolkit_name else {}
             ))
         return cls(tools=tools)
 

alita_sdk/tools/elastic/__init__.py

@@ -5,7 +5,7 @@ from pydantic import BaseModel, ConfigDict, create_model, Field, SecretStr
 
 from .api_wrapper import ELITEAElasticApiWrapper
 from ..base.tool import BaseAction
-from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
+from ..utils import clean_string, get_max_toolkit_length
 
 name = "elastic"
 
@@ -19,15 +19,13 @@ def get_tools(tool):
 
 class ElasticToolkit(BaseToolkit):
     tools: list[BaseTool] = []
-    toolkit_max_length: int = 0
 
     @staticmethod
     def toolkit_config_schema() -> BaseModel:
         selected_tools = {x['name']: x['args_schema'].schema() for x in ELITEAElasticApiWrapper.model_construct().get_available_tools()}
-        ElasticToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
         return create_model(
             name,
-            url=(str, Field(default=None, title="Elasticsearch URL", description="Elasticsearch URL", json_schema_extra={'toolkit_name': True, 'max_toolkit_length': ElasticToolkit.toolkit_max_length})),
+            url=(str, Field(default=None, title="Elasticsearch URL", description="Elasticsearch URL", json_schema_extra={'toolkit_name': True})),
             api_key=(
                 Optional[SecretStr],
                 Field(
@@ -48,15 +46,19 @@ class ElasticToolkit(BaseToolkit):
         elastic_api_wrapper = ELITEAElasticApiWrapper(**kwargs)
         available_tools = elastic_api_wrapper.get_available_tools()
         tools = []
-        prefix = clean_string(toolkit_name, ElasticToolkit.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''
         for tool in available_tools:
             if selected_tools and tool["name"] not in selected_tools:
                 continue
+            description = tool["description"]
+            if toolkit_name:
+                description = f"Toolkit: {toolkit_name}\n{description}"
+            description = description[:1000]
             tools.append(BaseAction(
                 api_wrapper=elastic_api_wrapper,
-                name=prefix + tool["name"],
-                description=tool["description"],
-                args_schema=tool["args_schema"]
+                name=tool["name"],
+                description=description,
+                args_schema=tool["args_schema"],
+                metadata={"toolkit_name": toolkit_name} if toolkit_name else {}
             ))
         return cls(tools=tools)