alita-sdk 0.3.282__py3-none-any.whl → 0.3.284__py3-none-any.whl

alita_sdk/runtime/tools/vectorstore_base.py

@@ -587,7 +587,7 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
 
         try:
             dispatch_custom_event(
-                name="thinking_step",
+                name="thinking_step_update",
                 data={
                     "message": message,
                     "tool_name": tool_name,

alita_sdk/tools/base_indexer_toolkit.py

@@ -158,15 +158,22 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         if clean_index:
             self._clean_index(collection_suffix)
         #
+        self._log_tool_event(f"Indexing data into collection with suffix '{collection_suffix}'. It can take some time...")
+        self._log_tool_event(f"Loading the documents to index...{kwargs}")
         documents = self._base_loader(**kwargs)
+        self._log_tool_event(f"Base documents were loaded. "
+                             f"Search for possible document duplicates and remove them from the indexing list...")
         documents = self._reduce_duplicates(documents, collection_suffix)
+        self._log_tool_event(f"Duplicates were removed. "
+                             f"Processing documents to collect dependencies and prepare them for indexing...")
         documents = self._extend_data(documents) # update content of not-reduced base document if needed (for sharepoint and similar)
         documents = self._collect_dependencies(documents) # collect dependencies for base documents
+        self._log_tool_event(f"Documents were processed. "
+                             f"Applying chunking tool '{chunking_tool}' if specified and preparing documents for indexing...")
         documents = self._apply_loaders_chunkers(documents, chunking_tool, chunking_config)
         list_documents = list(documents)
         self._clean_metadata(list_documents)
-
-        #
+        self._log_tool_event(f"Documents are ready for indexing. Total documents to index: {len(list_documents)}")
         return self._save_index(list_documents, collection_suffix=collection_suffix, progress_step=progress_step)
     
     def _apply_loaders_chunkers(self, documents: Generator[Document, None, None], chunking_tool: str=None, chunking_config=None) -> Generator[Document, None, None]:

alita_sdk/tools/elitea_base.py

@@ -576,6 +576,10 @@ class BaseCodeToolApiWrapper(BaseVectorStoreToolApiWrapper):
             raise ValueError("Expected a list of strings")
         return _files
 
+    def __get_branch(self, branch):
+       return (branch or getattr(self, 'active_branch', None)
+               or getattr(self, '_active_branch', None) or getattr(self, 'branch', None))
+
     def loader(self,
                branch: Optional[str] = None,
                whitelist: Optional[List[str]] = None,
@@ -601,7 +605,7 @@ class BaseCodeToolApiWrapper(BaseVectorStoreToolApiWrapper):
         """
         from .chunkers.code.codeparser import parse_code_files_for_db
 
-        _files = self.__handle_get_files("", branch or self.active_branch or self._active_branch)
+        _files = self.__handle_get_files("", self.__get_branch(branch))
         self._log_tool_event(message="Listing files in branch", tool_name="loader")
         logger.info(f"Files in branch: {_files}")
 
@@ -624,7 +628,7 @@ 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, branch=branch or self.active_branch or self._active_branch)
+                    file_content = self._read_file(file, self.__get_branch(branch))
                     if not file_content:
                         # empty file, skip
                         continue

alita_sdk/tools/figma/api_wrapper.py

@@ -249,7 +249,9 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
     ) -> Generator[Document, None, None]:
         # If both include and exclude are provided, use only include
         if file_keys_include:
+            self._log_tool_event(f"Loading files: {file_keys_include}")
             for file_key in file_keys_include:
+                self._log_tool_event(f"Loading file `{file_key}`")
                 file = self._client.get_file(file_key)
                 if not file:
                     raise ToolException(f"Unexpected error while retrieving file {file_key}. Probably file is under editing. Try again later.")
@@ -265,6 +267,7 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
                 }
                 yield Document(page_content=json.dumps(metadata), metadata=metadata)
         elif project_id:
+            self._log_tool_event(f"Loading project files from project `{project_id}`")
             files = json.loads(self.get_project_files(project_id)).get('files', [])
             for file in files:
                 if file_keys_exclude and file.get('key', '') in file_keys_exclude:
@@ -286,12 +289,14 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
 
     def _process_document(self, document: Document) -> Generator[Document, None, None]:
         file_key = document.metadata.get('id', '')
+        self._log_tool_event(f"Loading details (images) for `{file_key}`")
         #
         figma_pages = self._client.get_file(file_key).document.get('children', [])
         node_ids_include = document.metadata.pop('figma_pages_include', [])
         node_ids_exclude = document.metadata.pop('figma_pages_exclude', [])
         node_types_include = [t.lower() for t in document.metadata.pop('figma_nodes_include', [])]
         node_types_exclude = [t.lower() for t in document.metadata.pop('figma_nodes_exclude', [])]
+        self._log_tool_event(f"Included pages: {node_ids_include}. Excluded pages: {node_ids_exclude}.")
         if node_ids_include:
             figma_pages = [node for node in figma_pages if ('id' in node and node['id'].replace(':', '-') in node_ids_include)]
         elif node_ids_exclude:
@@ -310,7 +315,12 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
         ]
 
         images = self._client.get_file_images(file_key, node_ids).images or {}
-        for node_id, image_url in images.items():
+        total_images = len(images)
+        if total_images == 0:
+            logging.info(f"No images found for file {file_key}.")
+            return
+        progress_step = max(1, total_images // 10)
+        for idx, (node_id, image_url) in enumerate(images.items(), 1):
             if not image_url:
                 logging.warning(f"Image URL not found for node_id {node_id} in file {file_key}. Skipping.")
                 continue
@@ -321,17 +331,22 @@ class FigmaApiWrapper(NonCodeIndexerToolkit):
                     extension = f".{content_type.split('/')[-1]}" if content_type.startswith('image') else '.txt'
                     page_content = load_content_from_bytes(
                         file_content=response.content,
-                        extension=extension, llm = self.llm)
+                        extension=extension, llm=self.llm)
                     yield Document(
-                                    page_content=page_content,
-                                    metadata={
-                                        'id': file_key,
-                                        'updated_on': document.metadata.get('updated_on', ''),
-                                        'file_key': file_key,
-                                        'node_id': node_id,
-                                        'image_url': image_url
-                                    }
-                                )
+                        page_content=page_content,
+                        metadata={
+                            'id': node_id,
+                            'updated_on': document.metadata.get('updated_on', ''),
+                            'file_key': file_key,
+                            'node_id': node_id,
+                            'image_url': image_url
+                        }
+                    )
+            if idx % progress_step == 0 or idx == total_images:
+                percent = int((idx / total_images) * 100)
+                msg = f"Processed {idx}/{total_images} images ({percent}%) for file {file_key}."
+                logging.info(msg)
+                self._log_tool_event(msg)
 
     def _remove_metadata_keys(self):
         return super()._remove_metadata_keys() + ['figma_pages_include', 'figma_pages_exclude', 'figma_nodes_include', 'figma_nodes_exclude']

{alita_sdk-0.3.282.dist-info → alita_sdk-0.3.284.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.282
+Version: 0.3.284
 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-0.3.282.dist-info → alita_sdk-0.3.284.dist-info}/RECORD

@@ -119,7 +119,7 @@ alita_sdk/runtime/tools/prompt.py,sha256=nJafb_e5aOM1Rr3qGFCR-SKziU9uCsiP2okIMs9
 alita_sdk/runtime/tools/router.py,sha256=wCvZjVkdXK9dMMeEerrgKf5M790RudH68pDortnHSz0,1517
 alita_sdk/runtime/tools/tool.py,sha256=lE1hGi6qOAXG7qxtqxarD_XMQqTghdywf261DZawwno,5631
 alita_sdk/runtime/tools/vectorstore.py,sha256=PN_Im5pkbFR6vXUhlBppEwHEhsg-UsO9eYrMS8UstFk,35826
-alita_sdk/runtime/tools/vectorstore_base.py,sha256=CTAsQXImOHjlcddU2hoqyRAf8iNaDMTfr0pJbIaOG7o,27744
+alita_sdk/runtime/tools/vectorstore_base.py,sha256=AoTTkpygbcstzUQsgbK0eP0RdoAS5wU-qSbbbA9U-pU,27751
 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
@@ -131,8 +131,8 @@ alita_sdk/runtime/utils/toolkit_runtime.py,sha256=MU63Fpxj0b5_r1IUUc0Q3-PN9VwL7r
 alita_sdk/runtime/utils/toolkit_utils.py,sha256=I9QFqnaqfVgN26LUr6s3XlBlG6y0CoHURnCzG7XcwVs,5311
 alita_sdk/runtime/utils/utils.py,sha256=VXNLsdeTmf6snn9EtUyobv4yL-xzLhUcH8P_ORMifYc,675
 alita_sdk/tools/__init__.py,sha256=8oFahbggsv8h7hEqqeQ4iF6g2m85Ki17iSeknviCNis,10613
-alita_sdk/tools/base_indexer_toolkit.py,sha256=h3KnF4_tgAkxWUjW8djPUyNEKpI24kU6LDjCnJtxE-o,19322
-alita_sdk/tools/elitea_base.py,sha256=aoh4fjNHIem8jzPPqtvxD4PtkGgN3KBQwrMqb9f6k00,32991
+alita_sdk/tools/base_indexer_toolkit.py,sha256=3s8YRx_ambQQXGOKdlt_sRqREbrzFgm9zCWgxWsPHMU,20155
+alita_sdk/tools/elitea_base.py,sha256=EBCgrqfaHwyhq510svtDEB0i5pizazeIPHKD1acsKAk,33121
 alita_sdk/tools/non_code_indexer_toolkit.py,sha256=v9uq1POE1fQKCd152mbqDtF-HSe0qoDj83k4E5LAkMI,1080
 alita_sdk/tools/ado/__init__.py,sha256=u2tdDgufGuDb-7lIgKKQlqgStL9Wd1gzNmRNYems2c0,1267
 alita_sdk/tools/ado/utils.py,sha256=PTCludvaQmPLakF2EbCGy66Mro4-rjDtavVP-xcB2Wc,1252
@@ -233,7 +233,7 @@ alita_sdk/tools/custom_open_api/api_wrapper.py,sha256=sDSFpvEqpSvXHGiBISdQQcUecf
 alita_sdk/tools/elastic/__init__.py,sha256=iwnSRppRpzvJ1da2K3Glu8Uu41MhBDCYbguboLkEbW0,2818
 alita_sdk/tools/elastic/api_wrapper.py,sha256=pl8CqQxteJAGwyOhMcld-ZgtOTFwwbv42OITQVe8rM0,1948
 alita_sdk/tools/figma/__init__.py,sha256=hfe7FxMCCKnHNUdj9dCLuCu69pabBq6OmmlxODBXqzc,4410
-alita_sdk/tools/figma/api_wrapper.py,sha256=kpzs38qq3uc6pRB2LwwSW3P7Itcqs7hUFcrDUbCExzo,25044
+alita_sdk/tools/figma/api_wrapper.py,sha256=HCOl8upJl5_yjtrgy0A8mEWVkqIq5oPzUCJAlNfyPzc,25856
 alita_sdk/tools/github/__init__.py,sha256=2LLkgtm8mp5e1vlgx2VtPiUlV95iCeYLOXdWVz1kXP0,5092
 alita_sdk/tools/github/api_wrapper.py,sha256=uDwYckdnpYRJtb0uZnDkaz2udvdDLVxuCh1tSwspsiU,8411
 alita_sdk/tools/github/github_client.py,sha256=nxnSXsDul2PPbWvYZS8TmAFFmR-5ALyakNoV5LN2D4U,86617
@@ -347,8 +347,8 @@ alita_sdk/tools/zephyr_scale/api_wrapper.py,sha256=HOt9ShtJI_1tVPcwd3Rwk-VS0SMLq
 alita_sdk/tools/zephyr_squad/__init__.py,sha256=0AI_j27xVO5Gk5HQMFrqPTd4uvuVTpiZUicBrdfEpKg,2796
 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-0.3.282.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-alita_sdk-0.3.282.dist-info/METADATA,sha256=hfPjY5I-dvK_iVEukdJdK4zKc8hZz8hOBvMm9ZD0TWs,18897
-alita_sdk-0.3.282.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-alita_sdk-0.3.282.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
-alita_sdk-0.3.282.dist-info/RECORD,,
+alita_sdk-0.3.284.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+alita_sdk-0.3.284.dist-info/METADATA,sha256=4u6303venAnCzBB7n0UveeWvynBpZTAACQENr6amRqo,18897
+alita_sdk-0.3.284.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+alita_sdk-0.3.284.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
+alita_sdk-0.3.284.dist-info/RECORD,,