alita-sdk 0.3.208__tar.gz → 0.3.209__tar.gz

{alita_sdk-0.3.208 → alita_sdk-0.3.209}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.208
+Version: 0.3.209
 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-0.3.208 → alita_sdk-0.3.209}/alita_sdk/runtime/langchain/langraph_agent.py

@@ -9,7 +9,7 @@ from langchain_core.callbacks import dispatch_custom_event
 from langchain_core.messages import HumanMessage, AIMessage, SystemMessage, BaseMessage
 from langchain_core.runnables import Runnable
 from langchain_core.runnables import RunnableConfig
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, ToolException
 from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.graph import StateGraph
 from langgraph.graph.graph import END, START
@@ -506,10 +506,10 @@ def create_graph(
                     for toolkit, selected_tools in connected_tools.items():
                         for tool in selected_tools:
                             tool_names.append(f"{toolkit}___{tool}")
+                elif isinstance(connected_tools, list):
+                    # for cases when tools are provided as a list of names with already bound toolkit_name
+                    tool_names = connected_tools
                 
-                # Filter tools if specific tool names are provided
-                available_tools = []
-            
                 if tool_names:
                     # Filter tools by name
                     tool_dict = {tool.name: tool for tool in tools if isinstance(tool, BaseTool)}
@@ -580,7 +580,10 @@ def create_graph(
                     default_output=node['condition'].get('default_output', 'END')))
 
         # set default value for state variable at START
-        entry_point = clean_string(schema['entry_point'])
+        try:
+            entry_point = clean_string(schema['entry_point'])
+        except KeyError:
+            raise ToolException("Entry point is not defined in the schema. Please define 'entry_point' in the schema.")
         for key, value in state.items():
             if 'type' in value and 'value' in value:
                 # set default value for state variable if it is defined in the schema

{alita_sdk-0.3.208 → alita_sdk-0.3.209}/alita_sdk/runtime/tools/vectorstore.py

@@ -199,13 +199,12 @@ class VectorStoreWrapper(BaseToolApiWrapper):
             data = store.get(include=['documents', 'metadatas'])
             # re-structure data to be more usable
             for doc_str, meta, db_id in zip(data['documents'], data['metadatas'], data['ids']):
-                doc = json.loads(doc_str)
                 doc_id = str(meta['id'])
                 dependent_docs = meta.get(IndexerKeywords.DEPENDENT_DOCS.value, [])
                 parent_id = meta.get(IndexerKeywords.PARENT.value, -1)
                 result[doc_id] = {
                     'metadata': meta,
-                    'document': doc,
+                    'document': doc_str,
                     'id': db_id,
                     IndexerKeywords.DEPENDENT_DOCS.value: dependent_docs,
                     IndexerKeywords.PARENT.value: parent_id

{alita_sdk-0.3.208 → alita_sdk-0.3.209}/alita_sdk/tools/testrail/api_wrapper.py

@@ -11,6 +11,7 @@ from ..elitea_base import BaseVectorStoreToolApiWrapper, BaseIndexParams
 from langchain_core.documents import Document
 
 from ...runtime.utils.utils import IndexerKeywords
+from ..utils.content_parser import parse_file_content
 
 try:
     from alita_sdk.runtime.langchain.interfaces.llm_processor import get_embeddings
@@ -658,8 +659,12 @@ class TestrailAPIWrapper(BaseVectorStoreToolApiWrapper):
         page_content = "This filetype is not supported."
         if attachment['filetype'] == 'txt' :
             page_content =  self._client.get(endpoint=f"get_attachment/{attachment['id']}")
-        # TODO: add support for other file types
-        # use utility to handle different types (tools/utils)
+        else:
+            try:
+                attachment_path = self._client.attachments.get_attachment(attachment_id=attachment['id'], path=f"./{attachment['filename']}")
+                page_content = parse_file_content(file_name=attachment['filename'], file_content=attachment_path.read_bytes(), llm=self.llm, is_capture_image=True)
+            except Exception as e:
+                logger.error(f"Unable to parse page's content with type: {attachment['filetype']}: {e}")
         return page_content
 
     def _to_markup(self, data: List[Dict], output_format: str) -> str:

{alita_sdk-0.3.208 → alita_sdk-0.3.209}/alita_sdk/tools/utils/content_parser.py

@@ -11,9 +11,12 @@ import pymupdf
 from langchain_core.tools import ToolException
 from transformers import BlipProcessor, BlipForConditionalGeneration
 from langchain_core.messages import HumanMessage
+from logging import getLogger
 
 from ...runtime.langchain.tools.utils import bytes_to_base64
 
+logger = getLogger(__name__)
+
 image_processing_prompt='''
 You are an AI model designed for analyzing images. Your task is to accurately describe the content of the given image. Depending on the type of image, follow these specific instructions:
 
@@ -56,7 +59,33 @@ Be as precise and thorough as possible in your responses. If something is unclea
 
 IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'gif', 'bmp', 'tiff', 'webp', 'svg']
 
-def parse_file_content(file_name, file_content, is_capture_image: bool = False, page_number: int = None, sheet_name: str = None, llm=None):
+
+def parse_file_content(file_name=None, file_content=None, is_capture_image: bool = False, page_number: int = None,
+                       sheet_name: str = None, llm=None, file_path: str = None):
+    """Parse the content of a file based on its type and return the parsed content.
+
+    Args:
+        file_name (str): The name of the file to parse.
+        file_content (bytes): The content of the file as bytes.
+        is_capture_image (bool): Whether to capture images from the file.
+        page_number (int, optional): The specific page number to parse for PDF or PPTX files.
+        sheet_name (str, optional): The specific sheet name to parse for Excel files.
+        llm: The language model to use for image processing.
+        file_path (str, optional): The path to the file if it needs to be read from disk.
+    Returns:
+        str: The parsed content of the file.
+    Raises:
+        ToolException: If the file type is not supported or if there is an error reading the file.
+        """
+
+    if (file_path and (file_name or file_content)) or (not file_path and (not file_name or file_content is None)):
+        raise ToolException("Either (file_name and file_content) or file_path must be provided, but not both.")
+
+    if file_path:
+        file_content = file_to_bytes(file_path)
+        if file_content is None:
+            return ToolException(f"File not found or could not be read: {file_path}")
+        file_name = file_path.split('/')[-1]  # Extract file name from path
     if file_name.endswith('.txt'):
         return parse_txt(file_content)
     elif file_name.endswith('.docx'):
@@ -176,4 +205,25 @@ def __perform_llm_prediction_for_image(llm, image: bytes, image_format='png', pr
                 },
             ])
     ])
-    return f"\n[Image description: {result.content}]\n"
+    return f"\n[Image description: {result.content}]\n"
+
+def file_to_bytes(filepath):
+    """
+    Reads a file and returns its content as a bytes object.
+
+    Args:
+        filepath (str): The path to the file.
+
+    Returns:
+        bytes: The content of the file as a bytes object.
+    """
+    try:
+        with open(filepath, "rb") as f:
+            file_content_bytes = f.read()
+        return file_content_bytes
+    except FileNotFoundError:
+        logger.error(f"File not found: {filepath}")
+        return None
+    except Exception as e:
+        logger.error(f"Error reading file {filepath}: {e}")
+        return None

{alita_sdk-0.3.208 → alita_sdk-0.3.209}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.208
+Version: 0.3.209
 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-0.3.208 → alita_sdk-0.3.209}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.208"
+version = "0.3.209"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"