alita-sdk 0.3.369__py3-none-any.whl → 0.3.370__py3-none-any.whl

alita_sdk/runtime/tools/vectorstore_base.py

@@ -6,6 +6,8 @@ from typing import Any, Optional, List, Dict, Generator
 
 from langchain_core.documents import Document
 from langchain_core.messages import HumanMessage
+from langchain_core.tools import ToolException
+from psycopg.errors import DataException
 from pydantic import BaseModel, model_validator, Field
 
 from alita_sdk.tools.elitea_base import BaseToolApiWrapper
@@ -316,6 +318,15 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
                     if doc_id not in unique_docs or score > chunk_type_scores.get(doc_id, 0):
                         unique_docs[doc_id] = doc
                         chunk_type_scores[doc_id] = score
+            except DataException as dimException:
+                exception_str = str(dimException)
+                if 'different vector dimensions' in exception_str:
+                    logger.error(f"Data exception: {exception_str}")
+                    raise ToolException(f"Global search cannot be completed since collections were indexed using "
+                                        f"different embedding models. Use search within a single collection."
+                                        f"\nDetails: {exception_str}")
+                raise ToolException(f"Data exception during search. Possibly invalid filter: {exception_str}")
+
             except Exception as e:
                 logger.warning(f"Error searching for document chunks: {str(e)}")
             

alita_sdk/tools/confluence/api_wrapper.py

@@ -815,6 +815,10 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
         from .loader import AlitaConfluenceLoader
         from copy import copy
         content_format = kwargs.get('content_format', 'view').lower()
+
+        self._index_include_attachments = kwargs.get('include_attachments', False)
+        self._include_extensions = kwargs.get('include_extensions', [])
+        self._skip_extensions = kwargs.get('skip_extensions', [])
         base_params = {
             'url': self.base_url,
             'space_key': self.space,
@@ -847,65 +851,79 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
 
     def _process_document(self, document: Document) -> Generator[Document, None, None]:
         try:
-            page_id = document.metadata.get('id')
-            attachments = self.client.get_attachments_from_content(page_id)
-            if not attachments or not attachments.get('results'):
-                return f"No attachments found for page ID {page_id}."
-
-            # Get attachment history for created/updated info
-            history_map = {}
-            for attachment in attachments['results']:
-                try:
-                    hist = self.client.history(attachment['id'])
-                    history_map[attachment['id']] = hist
-                except Exception as e:
-                    logger.warning(f"Failed to fetch history for attachment {attachment.get('title', '')}: {str(e)}")
-                    history_map[attachment['id']] = None
-
-            import re
-            for attachment in attachments['results']:
-                title = attachment.get('title', '')
-                file_ext = title.lower().split('.')[-1] if '.' in title else ''
-
-                media_type = attachment.get('metadata', {}).get('mediaType', '')
-                # Core metadata extraction with history
-                hist = history_map.get(attachment['id']) or {}
-                created_by = hist.get('createdBy', {}).get('displayName', '') if hist else attachment.get('creator', {}).get('displayName', '')
-                created_date = hist.get('createdDate', '') if hist else attachment.get('created', '')
-                last_updated = hist.get('lastUpdated', {}).get('when', '') if hist else ''
+            if self._index_include_attachments:
+                page_id = document.metadata.get('id')
+                attachments = self.client.get_attachments_from_content(page_id)
+                if not attachments or not attachments.get('results'):
+                    return f"No attachments found for page ID {page_id}."
+
+                # Get attachment history for created/updated info
+                history_map = {}
+                for attachment in attachments['results']:
+                    try:
+                        hist = self.client.history(attachment['id'])
+                        history_map[attachment['id']] = hist
+                    except Exception as e:
+                        logger.warning(f"Failed to fetch history for attachment {attachment.get('title', '')}: {str(e)}")
+                        history_map[attachment['id']] = None
+
+                import re
+                for attachment in attachments['results']:
+                    title = attachment.get('title', '')
+                    file_ext = title.lower().split('.')[-1] if '.' in title else ''
+
+                    # Re-verify extension filters
+                    # Check if file should be skipped based on skip_extensions
+                    if any(re.match(pattern.replace('*', '.*') + '$', title, re.IGNORECASE)
+                           for pattern in self._skip_extensions):
+                        continue
+
+                    # Check if file should be included based on include_extensions
+                    # If include_extensions is empty, process all files (that weren't skipped)
+                    if self._include_extensions and not (
+                    any(re.match(pattern.replace('*', '.*') + '$', title, re.IGNORECASE)
+                        for pattern in self._include_extensions)):
+                        continue
+
+                    media_type = attachment.get('metadata', {}).get('mediaType', '')
+                    # Core metadata extraction with history
+                    hist = history_map.get(attachment['id']) or {}
+                    created_by = hist.get('createdBy', {}).get('displayName', '') if hist else attachment.get('creator', {}).get('displayName', '')
+                    created_date = hist.get('createdDate', '') if hist else attachment.get('created', '')
+                    last_updated = hist.get('lastUpdated', {}).get('when', '') if hist else ''
+
+                    metadata = {
+                        'name': title,
+                        'size': attachment.get('extensions', {}).get('fileSize', None),
+                        'creator': created_by,
+                        'created': created_date,
+                        'updated': last_updated,
+                        'media_type': media_type,
+                        'labels': [label['name'] for label in
+                                   attachment.get('metadata', {}).get('labels', {}).get('results', [])],
+                        'download_url': self.base_url.rstrip('/') + attachment['_links']['download'] if attachment.get(
+                            '_links', {}).get('download') else None
+                    }
 
-                metadata = {
-                    'name': title,
-                    'size': attachment.get('extensions', {}).get('fileSize', None),
-                    'creator': created_by,
-                    'created': created_date,
-                    'updated': last_updated,
-                    'media_type': media_type,
-                    'labels': [label['name'] for label in
-                               attachment.get('metadata', {}).get('labels', {}).get('results', [])],
-                    'download_url': self.base_url.rstrip('/') + attachment['_links']['download'] if attachment.get(
-                        '_links', {}).get('download') else None
-                }
+                    download_url = self.base_url.rstrip('/') + attachment['_links']['download']
 
-                download_url = self.base_url.rstrip('/') + attachment['_links']['download']
+                    try:
+                        resp = self.client.request(method="GET", path=download_url[len(self.base_url):], advanced_mode=True)
+                        if resp.status_code == 200:
+                            content = resp.content
+                        else:
+                            content = f"[Failed to download {download_url}: HTTP status code {resp.status_code}]"
+                    except Exception as e:
+                        content = f"[Error downloading content: {str(e)}]"
 
-                try:
-                    resp = self.client.request(method="GET", path=download_url[len(self.base_url):], advanced_mode=True)
-                    if resp.status_code == 200:
-                        content = resp.content
+                    if isinstance(content, str):
+                        yield Document(page_content=content, metadata=metadata)
                     else:
-                        content = f"[Failed to download {download_url}: HTTP status code {resp.status_code}]"
-                except Exception as e:
-                    content = f"[Error downloading content: {str(e)}]"
-
-                if isinstance(content, str):
-                    yield Document(page_content=content, metadata=metadata)
-                else:
-                    yield Document(page_content="", metadata={
-                        **metadata,
-                        IndexerKeywords.CONTENT_FILE_NAME.value: f".{file_ext}",
-                        IndexerKeywords.CONTENT_IN_BYTES.value: content
-                    })
+                        yield Document(page_content="", metadata={
+                            **metadata,
+                            IndexerKeywords.CONTENT_FILE_NAME.value: f".{file_ext}",
+                            IndexerKeywords.CONTENT_IN_BYTES.value: content
+                        })
         except Exception as e:
             yield from ()
 
@@ -1648,6 +1666,13 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
             "include_restricted_content": (Optional[bool], Field(description="Include restricted content.", default=False)),
             "include_archived_content": (Optional[bool], Field(description="Include archived content.", default=False)),
             "include_attachments": (Optional[bool], Field(description="Include attachments.", default=False)),
+            'include_extensions': (Optional[List[str]], Field(
+                description="List of file extensions to include when processing attachments: i.e. ['*.png', '*.jpg']. "
+                            "If empty, all files will be processed (except skip_extensions).",
+                default=[])),
+            'skip_extensions': (Optional[List[str]], Field(
+                description="List of file extensions to skip when processing attachments: i.e. ['*.png', '*.jpg']",
+                default=[])),
             "include_comments": (Optional[bool], Field(description="Include comments.", default=False)),
             "include_labels": (Optional[bool], Field(description="Include labels.", default=True)),
             "ocr_languages": (Optional[str], Field(description="OCR languages for processing attachments.", default='eng')),

{alita_sdk-0.3.369.dist-info → alita_sdk-0.3.370.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.369
+Version: 0.3.370
 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-0.3.369.dist-info → alita_sdk-0.3.370.dist-info}/RECORD

@@ -123,7 +123,7 @@ alita_sdk/runtime/tools/router.py,sha256=p7e0tX6YAWw2M2Nq0A_xqw1E2P-Xz1DaJvhUstf
 alita_sdk/runtime/tools/sandbox.py,sha256=WNz-aUMtkGCPg84dDy_0BPkyp-6YjoYB-xjIEFFrtKw,11601
 alita_sdk/runtime/tools/tool.py,sha256=lE1hGi6qOAXG7qxtqxarD_XMQqTghdywf261DZawwno,5631
 alita_sdk/runtime/tools/vectorstore.py,sha256=8vRhi1lGFEs3unvnflEi2p59U2MfV32lStpEizpDms0,34467
-alita_sdk/runtime/tools/vectorstore_base.py,sha256=4POq0NZ8FnMANop2JweeRNK9ViWcrpBM1y4Jl22E46E,26801
+alita_sdk/runtime/tools/vectorstore_base.py,sha256=1DYmMQEBMLetxQgi6D9Wd_vM_xVCa9qGTAfLOo2kNC0,27533
 alita_sdk/runtime/utils/AlitaCallback.py,sha256=E4LlSBuCHWiUq6W7IZExERHZY0qcmdjzc_rJlF2iQIw,7356
 alita_sdk/runtime/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 alita_sdk/runtime/utils/constants.py,sha256=Xntx1b_uxUzT4clwqHA_U6K8y5bBqf_4lSQwXdcWrp4,13586
@@ -230,7 +230,7 @@ alita_sdk/tools/code/loaders/codesearcher.py,sha256=XoXXZtIQZhvjIwZlnl_4wVGHC-3s
 alita_sdk/tools/code/sonar/__init__.py,sha256=iPqj2PnUY4-btJjaDeWIPdn-c9L_uCr_qOoP_uwRoXw,3360
 alita_sdk/tools/code/sonar/api_wrapper.py,sha256=nNqxcWN_6W8c0ckj-Er9HkNuAdgQLoWBXh5UyzNutis,2653
 alita_sdk/tools/confluence/__init__.py,sha256=zRnPBM1c7VTRTS955HNc7AEGV5t8ACc2f9wBXmmeXao,6845
-alita_sdk/tools/confluence/api_wrapper.py,sha256=lUhGzcvYgTXx1bYr2lgK5t2lZFrnTWF4PJ_CWT8q-Ao,87805
+alita_sdk/tools/confluence/api_wrapper.py,sha256=cHIr0EnXZVGQMepcaIcFgMfyTKjlkKGbAd0z79pf-bo,89544
 alita_sdk/tools/confluence/loader.py,sha256=4bf5qrJMEiJzuZp2NlxO2XObLD1w7fxss_WyMUpe8sg,9290
 alita_sdk/tools/confluence/utils.py,sha256=Lxo6dBD0OlvM4o0JuK6qeB_4LV9BptiwJA9e1vqNcDw,435
 alita_sdk/tools/custom_open_api/__init__.py,sha256=9aT5SPNPWcJC6jMZEM-3rUCXVULj_3-qJLQKmnreKNo,2537
@@ -352,8 +352,8 @@ alita_sdk/tools/zephyr_scale/api_wrapper.py,sha256=kT0TbmMvuKhDUZc0i7KO18O38JM9S
 alita_sdk/tools/zephyr_squad/__init__.py,sha256=0ne8XLJEQSLOWfzd2HdnqOYmQlUliKHbBED5kW_Vias,2895
 alita_sdk/tools/zephyr_squad/api_wrapper.py,sha256=kmw_xol8YIYFplBLWTqP_VKPRhL_1ItDD0_vXTe_UuI,14906
 alita_sdk/tools/zephyr_squad/zephyr_squad_cloud_client.py,sha256=R371waHsms4sllHCbijKYs90C-9Yu0sSR3N4SUfQOgU,5066
-alita_sdk-0.3.369.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-alita_sdk-0.3.369.dist-info/METADATA,sha256=1fgFT8CTai8He4mId8cLCZhlVTYl6-pkFpBGUDh5Hds,19071
-alita_sdk-0.3.369.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-alita_sdk-0.3.369.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
-alita_sdk-0.3.369.dist-info/RECORD,,
+alita_sdk-0.3.370.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+alita_sdk-0.3.370.dist-info/METADATA,sha256=7o5P_ba4fUU5FVQU9htx-olWpTUnrpVOcfl2o3DwSEs,19071
+alita_sdk-0.3.370.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+alita_sdk-0.3.370.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
+alita_sdk-0.3.370.dist-info/RECORD,,