alita-sdk 0.3.329__tar.gz → 0.3.331__tar.gz

{alita_sdk-0.3.329 → alita_sdk-0.3.331}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.329
+Version: 0.3.331
 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-0.3.329 → alita_sdk-0.3.331}/alita_sdk/runtime/langchain/assistant.py

@@ -34,6 +34,7 @@ class Assistant:
         self.app_type = app_type
         self.memory = memory
         self.store = store
+        self.max_iterations = data.get('meta', {}).get('step_limit', 25)
 
         logger.debug("Data for agent creation: %s", data)
         logger.info("App type: %s", app_type)
@@ -145,7 +146,8 @@ class Assistant:
     def _agent_executor(self, agent: Any):
         return AgentExecutor.from_agent_and_tools(agent=agent, tools=self.tools,
                                                   verbose=True, handle_parsing_errors=True,
-                                                  max_execution_time=None, return_intermediate_steps=True)
+                                                  max_execution_time=None, return_intermediate_steps=True,
+                                                  max_iterations=self.max_iterations)
 
     def getAgentExecutor(self):
         # Exclude compiled graph runnables from simple tool agents

{alita_sdk-0.3.329 → alita_sdk-0.3.331}/alita_sdk/runtime/langchain/document_loaders/AlitaTextLoader.py

@@ -1,4 +1,4 @@
-from typing import Iterator
+from typing import Iterator, Generator
 
 from langchain_core.documents import Document
 
@@ -6,6 +6,9 @@ from langchain_community.document_loaders.base import BaseLoader
 from langchain_community.document_loaders.helpers import detect_file_encodings
 from langchain_core.tools import ToolException
 
+from alita_sdk.tools.chunkers import markdown_chunker
+
+
 class AlitaTextLoader(BaseLoader):
 
     def __init__(self, **kwargs):
@@ -19,6 +22,8 @@ class AlitaTextLoader(BaseLoader):
             raise ToolException("'file_path' or 'file_content' parameter should be provided.")
         self.encoding = kwargs.get('encoding', 'utf-8')
         self.autodetect_encoding = kwargs.get('autodetect_encoding', False)
+        self.max_tokens=kwargs.get('max_tokens', 1024)
+        self.token_overlap = kwargs.get('token_overlap', 10)
 
     def get_content(self):
         text = ""
@@ -59,8 +64,16 @@ class AlitaTextLoader(BaseLoader):
 
         return text
 
+    def generate_document(self, text, metadata) -> Generator[Document, None, None]:
+        yield Document(page_content=text, metadata=metadata)
+
     def lazy_load(self) -> Iterator[Document]:
         """Load from file path."""
         text = self.get_content()
         metadata = {"source": str(self.file_path) if hasattr(self, 'file_path') else self.file_name}
-        yield Document(page_content=text, metadata=metadata)
+        chunks = markdown_chunker(file_content_generator=self.generate_document(text, metadata),
+                                  config={
+                                      "max_tokens": self.max_tokens,
+                                      "token_overlap": self.token_overlap
+                                  })
+        yield from chunks

{alita_sdk-0.3.329 → alita_sdk-0.3.331}/alita_sdk/tools/utils/content_parser.py

@@ -1,4 +1,5 @@
 import os
+import re
 import tempfile
 from logging import getLogger
 from pathlib import Path
@@ -8,6 +9,7 @@ from langchain_core.documents import Document
 from langchain_core.tools import ToolException
 
 from alita_sdk.runtime.langchain.document_loaders.constants import loaders_map, LoaderProperties
+from ...runtime.langchain.document_loaders.AlitaTextLoader import AlitaTextLoader
 from ...runtime.utils.utils import IndexerKeywords
 
 logger = getLogger(__name__)
@@ -231,7 +233,8 @@ def process_content_by_type(content, filename: str, llm=None, chunking_config=No
     """Process the content of a file based on its type using a configured loader."""
     temp_file_path = None
     try:
-        extension = "." + filename.split('.')[-1].lower()
+        match = re.search(r'\.([^.]+)$', filename)
+        extension = f".{match.group(1).lower()}" if match else ".txt"
 
         with tempfile.NamedTemporaryFile(mode='w+b', suffix=extension, delete=False) as temp_file:
             temp_file_path = temp_file.name

{alita_sdk-0.3.329 → alita_sdk-0.3.331}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.329
+Version: 0.3.331
 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-0.3.329 → alita_sdk-0.3.331}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.329"
+version = "0.3.331"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"