alita-sdk 0.3.292__tar.gz → 0.3.294__tar.gz

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.292
+Version: 0.3.294
 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-0.3.292 → alita_sdk-0.3.294}/alita_sdk/runtime/langchain/document_loaders/constants.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from langchain_community.document_loaders import (
-    UnstructuredMarkdownLoader,
     AirbyteJSONLoader, UnstructuredHTMLLoader,
     PythonLoader)
 
@@ -26,43 +25,49 @@ from .AlitaPDFLoader import AlitaPDFLoader
 from .AlitaPowerPointLoader import AlitaPowerPointLoader
 from .AlitaTextLoader import AlitaTextLoader
 from .AlitaMarkdownLoader import AlitaMarkdownLoader
+from enum import Enum
+
+class LoaderProperties(Enum):
+    LLM = 'llm'
+    PROMPT = 'prompt'
+    PROMPT_DEFAULT = 'prompt_default'
 
 loaders_map = {
     '.png': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value],
     },
     '.jpg': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.jpeg': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.gif': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.bmp': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.svg': {
         'class': AlitaImageLoader,
         'is_multimodal_processing': True,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.txt': {
         'class': AlitaTextLoader,
@@ -119,7 +124,7 @@ loaders_map = {
             'raw_content': False,
             'cleanse': False
         },
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.xls': {
         'class': AlitaExcelLoader,
@@ -128,13 +133,13 @@ loaders_map = {
             'raw_content': False,
             'cleanse': False
         },
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.pdf': {
         'class': AlitaPDFLoader,
         'is_multimodal_processing': False,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.docx': {
         'class': AlitaDocxMammothLoader,
@@ -142,7 +147,7 @@ loaders_map = {
         'kwargs': {
             'extract_images': True
         },
-        'allowed_to_override': ['max_tokens', 'mode']
+        'allowed_to_override': ['max_tokens', 'mode', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.json': {
         'class': AlitaJSONLoader,
@@ -160,13 +165,13 @@ loaders_map = {
         'class': UnstructuredHTMLLoader,
         'is_multimodal_processing': False,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.html': {
         'class': UnstructuredHTMLLoader,
         'is_multimodal_processing': False,
         'kwargs': {},
-        'allowed_to_override': ['max_tokens']
+        'allowed_to_override': ['max_tokens', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.ppt': {
         'class': AlitaPowerPointLoader,
@@ -174,7 +179,7 @@ loaders_map = {
         'kwargs': {
             'mode': 'paged'
         },
-        'allowed_to_override': ['max_tokens', 'mode']
+        'allowed_to_override': ['max_tokens', 'mode', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.pptx': {
         'class': AlitaPowerPointLoader,
@@ -182,7 +187,7 @@ loaders_map = {
         'kwargs': {
             'mode': 'paged'
         },
-        'allowed_to_override': ['max_tokens', 'mode']
+        'allowed_to_override': ['max_tokens', 'mode', LoaderProperties.LLM.value, LoaderProperties.PROMPT.value, LoaderProperties.PROMPT_DEFAULT.value]
     },
     '.py': {
         'class': PythonLoader,

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/alita_sdk/tools/chunkers/code/codeparser.py

@@ -79,7 +79,7 @@ def parse_code_files_for_db(file_content_generator: Generator[str, None, None],
                     for splitted_document in splitted_documents:
                         metadata = {
                             "filename": file_name,
-                            "method_name": node.name,
+                            "method_name": node.name if node.name else 'unknown',
                             "language": programming_language.value,
                         }
                         commit_hash = data.get("commit_hash")

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/alita_sdk/tools/elitea_base.py

@@ -628,7 +628,11 @@ class BaseCodeToolApiWrapper(BaseVectorStoreToolApiWrapper):
             for idx, file in enumerate(_files, 1):
                 if is_whitelisted(file) and not is_blacklisted(file):
                     # read file ONLY if it matches whitelist and does not match blacklist
-                    file_content = self._read_file(file, self.__get_branch(branch))
+                    try:
+                        file_content = self._read_file(file, self.__get_branch(branch))
+                    except Exception as e:
+                        logger.error(f"Failed to read file {file}: {e}")
+                        file_content = ""
                     if not file_content:
                         # empty file, skip
                         continue

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/alita_sdk/tools/gitlab/api_wrapper.py

@@ -1,7 +1,7 @@
 # api_wrapper.py
 from typing import Any, Dict, List, Optional
 import fnmatch
-from alita_sdk.tools.elitea_base import BaseCodeToolApiWrapper
+from ...tools.elitea_base import BaseCodeToolApiWrapper
 from pydantic import create_model, Field, model_validator, SecretStr, PrivateAttr
 
 AppendFileModel = create_model(
@@ -110,7 +110,7 @@ class GitLabAPIWrapper(BaseCodeToolApiWrapper):
     @classmethod
     def validate_toolkit(cls, values: Dict) -> Dict:
         try:
-            import gitlab
+           import gitlab
         except ImportError:
             raise ImportError(
                 "python-gitlab is not installed. "

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/alita_sdk/tools/utils/content_parser.py

@@ -7,7 +7,7 @@ from typing import Generator, List
 from langchain_core.documents import Document
 from langchain_core.tools import ToolException
 
-from alita_sdk.runtime.langchain.document_loaders.constants import loaders_map
+from alita_sdk.runtime.langchain.document_loaders.constants import loaders_map, LoaderProperties
 from ...runtime.utils.utils import IndexerKeywords
 
 logger = getLogger(__name__)
@@ -52,8 +52,6 @@ Highlight any visible details that could help in understanding the image.
 Be as precise and thorough as possible in your responses. If something is unclear or illegible, state that explicitly.
 '''
 
-IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'gif', 'bmp', 'tiff', 'webp', 'svg']
-
 
 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, excel_by_sheets: bool = False) -> str | ToolException:
@@ -234,8 +232,11 @@ def process_content_by_type(document: Document, content, extension_source: str,
             if chunking_config and (users_config_for_extension := chunking_config.get(extension, {})):
                 for key in set(users_config_for_extension.keys()) & set(allowed_to_override):
                     loader_kwargs[key] = users_config_for_extension[key]
-            loader_kwargs['llm'] = llm
-            loader_kwargs['prompt'] = image_processing_prompt
+            if LoaderProperties.LLM.value in loader_kwargs:
+                loader_kwargs[LoaderProperties.LLM.value] = llm
+            if LoaderProperties.PROMPT_DEFAULT.value in loader_kwargs:
+                loader_kwargs.pop(LoaderProperties.PROMPT_DEFAULT.value)
+                loader_kwargs[LoaderProperties.PROMPT.value] = image_processing_prompt
             loader = loader_cls(file_path=temp_file_path, **loader_kwargs)
             counter = 1
             try:

{alita_sdk-0.3.292 → alita_sdk-0.3.294}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.292
+Version: 0.3.294
 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-0.3.292 → alita_sdk-0.3.294}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.292"
+version = "0.3.294"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"