alita-sdk 0.3.380__py3-none-any.whl → 0.3.382__py3-none-any.whl

alita_sdk/runtime/tools/vectorstore.py

@@ -414,7 +414,8 @@ class VectorStoreWrapper(BaseToolApiWrapper):
                 return {"status": "error", "message": f"Error: {format_exc()}"}
         if _documents:
             add_documents(vectorstore=self.vectorstore, documents=_documents)
-        return {"status": "ok", "message": f"successfully indexed {documents_count} documents"}
+        return {"status": "ok", "message": f"successfully indexed {documents_count} documents" if documents_count > 0
+        else "No new documents to index."}
 
     def search_documents(self, query:str, doctype: str = 'code', 
                          filter:dict|str={}, cut_off: float=0.5,

alita_sdk/runtime/tools/vectorstore_base.py

@@ -308,7 +308,8 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
                 return {"status": "error", "message": f"Error: {format_exc()}"}
         if _documents:
             add_documents(vectorstore=self.vectorstore, documents=_documents)
-        return {"status": "ok", "message": f"successfully indexed {documents_count} documents"}
+        return {"status": "ok", "message": f"successfully indexed {documents_count} documents" if documents_count > 0
+        else "no documents to index"}
 
     def search_documents(self, query:str, doctype: str = 'code', 
                          filter:dict|str={}, cut_off: float=0.5,

alita_sdk/tools/base_indexer_toolkit.py

@@ -161,8 +161,6 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
             if clean_index:
                 self._clean_index(index_name)
             #
-            self.index_meta_init(index_name, kwargs)
-            #
             self._log_tool_event(f"Indexing data into collection with suffix '{index_name}'. It can take some time...")
             self._log_tool_event(f"Loading the documents to index...{kwargs}")
             documents = self._base_loader(**kwargs)
@@ -176,11 +174,13 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                                  f"Processing documents to collect dependencies and prepare them for indexing...")
             self._save_index_generator(documents, documents_count, chunking_tool, chunking_config, index_name=index_name, result=result)
             #
-            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_COMPLETED.value, result["count"])
+            results_count = result["count"]
+            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_COMPLETED.value, results_count)
             #
-            return {"status": "ok", "message": f"successfully indexed {result["count"]} documents"}
+            return {"status": "ok", "message": f"successfully indexed {results_count} documents" if results_count > 0
+            else "no new documents to index"}
         except Exception as e:
-            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_FAILED.value, result["count"])
+            self.index_meta_update(index_name, IndexerKeywords.INDEX_META_FAILED.value, results_count)
             raise e
             
 
@@ -455,39 +455,6 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
             reranking_config=reranking_config, 
             extended_search=extended_search
         )
-    
-    def index_meta_init(self, index_name: str, index_configuration: dict[str, Any]):
-        index_meta_raw = super().get_index_meta(index_name)
-        from ..runtime.langchain.interfaces.llm_processor import add_documents
-        created_on = time.time()
-        metadata = {
-            "collection": index_name,
-            "type": IndexerKeywords.INDEX_META_TYPE.value,
-            "indexed": 0,
-            "state": IndexerKeywords.INDEX_META_IN_PROGRESS.value,
-            "index_configuration": index_configuration,
-            "created_on": created_on,
-            "updated_on": created_on,
-            "history": "[]",
-        }
-        index_meta_ids = None
-        #
-        if index_meta_raw:
-            history_raw = index_meta_raw.get("metadata", {}).get("history", "[]")
-            if isinstance(history_raw, str) and history_raw.strip():
-                try:
-                    history = json.loads(history_raw)
-                except (json.JSONDecodeError, TypeError):
-                    history = []
-            else:
-                history = []
-            new_history_item = {k: v for k, v in index_meta_raw.get("metadata", {}).items() if k != "history"}
-            history.append(new_history_item)
-            metadata["history"] = json.dumps(history)
-            index_meta_ids = [index_meta_raw.get("id")]
-        #
-        index_meta_doc = Document(page_content=f"{IndexerKeywords.INDEX_META_TYPE.value}_{index_name}", metadata=metadata)
-        add_documents(vectorstore=self.vectorstore, documents=[index_meta_doc], ids=index_meta_ids)
 
     def index_meta_update(self, index_name: str, state: str, result: int):
         index_meta_raw = super().get_index_meta(index_name)

alita_sdk/tools/confluence/api_wrapper.py

@@ -7,12 +7,14 @@ from json import JSONDecodeError
 from typing import Optional, List, Any, Dict, Callable, Generator, Literal
 
 import requests
+from atlassian.errors import ApiError
 from langchain_community.document_loaders.confluence import ContentFormat
 from langchain_core.documents import Document
 from langchain_core.messages import HumanMessage
 from langchain_core.tools import ToolException
 from markdownify import markdownify
 from pydantic import Field, PrivateAttr, model_validator, create_model, SecretStr
+from requests import HTTPError
 from tenacity import retry, stop_after_attempt, wait_exponential, before_sleep_log
 
 from alita_sdk.tools.non_code_indexer_toolkit import NonCodeIndexerToolkit
@@ -194,6 +196,7 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
     keep_markdown_format: Optional[bool] = True
     ocr_languages: Optional[str] = None
     keep_newlines: Optional[bool] = True
+    _errors: Optional[list[str]] = None
     _image_cache: ImageDescriptionCache = PrivateAttr(default_factory=ImageDescriptionCache)
 
     @model_validator(mode='before')
@@ -498,7 +501,9 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
         restrictions = self.client.get_all_restrictions_for_content(page["id"])
 
         return (
-                page["status"] == "current"
+                (page["status"] == "current"
+                # allow user to see archived content if needed
+                 or page["status"] == "archived")
                 and not restrictions["read"]["restrictions"]["user"]["results"]
                 and not restrictions["read"]["restrictions"]["group"]["results"]
         )
@@ -518,18 +523,34 @@ class ConfluenceAPIWrapper(NonCodeIndexerToolkit):
                 ),
                 before_sleep=before_sleep_log(logger, logging.WARNING),
             )(self.client.get_page_by_id)
-            page = get_page(
-                page_id=page_id, expand=f"{self.content_format.value},version"
-            )
+            try:
+                page = get_page(
+                    page_id=page_id, expand=f"{self.content_format.value},version"
+                )
+            except (ApiError, HTTPError) as e:
+                logger.error(f"Error fetching page with ID {page_id}: {e}")
+                page_content_temp = f"Confluence API Error: cannot fetch the page with ID {page_id}: {e}"
+                # store errors
+                if self._errors is None:
+                    self._errors = []
+                self._errors.append(page_content_temp)
+                return Document(page_content=page_content_temp,
+                                metadata={})
             if not self.include_restricted_content and not self.is_public_page(page):
                 continue
             yield self.process_page(page, skip_images)
 
+    def _log_errors(self):
+        """ Log errors encountered during toolkit execution. """
+        if self._errors:
+            logger.info(f"Errors encountered during toolkit execution: {self._errors}")
+
     def read_page_by_id(self, page_id: str, skip_images: bool = False):
         """Reads a page by its id in the Confluence space. If id is not available, but there is a title - use get_page_id first."""
         result = list(self.get_pages_by_id([page_id], skip_images))
         if not result:
-            "Page not found"
+            return f"Pages not found. Errors: {self._errors}" if self._errors \
+                else "Pages not found or you do not have access to them."
         return result[0].page_content
         # return self._strip_base64_images(result[0].page_content) if skip_images else result[0].page_content
 

alita_sdk/tools/vector_adapters/VectorStoreAdapter.py

@@ -145,7 +145,7 @@ class PGVectorAdapter(VectorStoreAdapter):
 
         result = {}
         try:
-            vectorstore_wrapper._log_data("Retrieving already indexed data from PGVector vectorstore",
+            vectorstore_wrapper._log_tool_event("Retrieving already indexed data from PGVector vectorstore",
                            tool_name="get_indexed_data")
             store = vectorstore_wrapper.vectorstore
             with Session(store.session_maker.bind) as session:

{alita_sdk-0.3.380.dist-info → alita_sdk-0.3.382.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.380
+Version: 0.3.382
 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-0.3.380.dist-info → alita_sdk-0.3.382.dist-info}/RECORD

@@ -123,8 +123,8 @@ alita_sdk/runtime/tools/prompt.py,sha256=nJafb_e5aOM1Rr3qGFCR-SKziU9uCsiP2okIMs9
 alita_sdk/runtime/tools/router.py,sha256=p7e0tX6YAWw2M2Nq0A_xqw1E2P-Xz1DaJvhUstfoZn4,1584
 alita_sdk/runtime/tools/sandbox.py,sha256=CBPaHwGv74FiHbELuwLBEvB2C-HhbptUnSMipzJUSZA,14282
 alita_sdk/runtime/tools/tool.py,sha256=lE1hGi6qOAXG7qxtqxarD_XMQqTghdywf261DZawwno,5631
-alita_sdk/runtime/tools/vectorstore.py,sha256=FsnxdnvMK5bUEFxz0eeSHeNpVOk2gxOeXjoSlvCo8rs,34327
-alita_sdk/runtime/tools/vectorstore_base.py,sha256=lNz6bOMpHOY8JiHT7BkoDbyj3kLykcKlCx4zOu_IgPE,28252
+alita_sdk/runtime/tools/vectorstore.py,sha256=0SzfY1dYrGr7YUapJzXY01JFyzLv36dPjwHzs1XZIM4,34392
+alita_sdk/runtime/tools/vectorstore_base.py,sha256=k_6LAhhBJEs5SXCQJI3bBvJLQli6_3pHjqF6SCQGJGc,28312
 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
@@ -136,7 +136,7 @@ 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=PJK8A-JVIzY1IowOjGG8DIqsIiEFe65qDKvFcjJCKWA,1041
 alita_sdk/tools/__init__.py,sha256=NrZyTEdEhmO1NnAR9RFMQ05Mb-kgu68mAQz3n5r0HYs,10692
-alita_sdk/tools/base_indexer_toolkit.py,sha256=i0S3tIdXrWoRx5B5v0cQMArnmOTsinC9SMLihlEcdxM,26801
+alita_sdk/tools/base_indexer_toolkit.py,sha256=RtFyGTWcnfXVKqTPvThjh42wg0Yp1TbLsPE6pnvIjko,25264
 alita_sdk/tools/code_indexer_toolkit.py,sha256=p3zVnCnQTUf7JUGra9Rl6GEK2W1-hvvz0Xsgz0v0muM,7292
 alita_sdk/tools/elitea_base.py,sha256=34fmVdYgd2YXifU5LFNjMQysr4OOIZ6AOZjq4GxLgSw,34417
 alita_sdk/tools/non_code_indexer_toolkit.py,sha256=6Lrqor1VeSLbPLDHAfg_7UAUqKFy1r_n6bdsc4-ak98,1315
@@ -231,7 +231,7 @@ 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=1HZftLQFzpNwGSN-9LPp8RQr1X-0fsKzmFlc-WEadZU,89545
+alita_sdk/tools/confluence/api_wrapper.py,sha256=5U6GIO65o0WoS_4f-Rci3n6CsCh4TGeXJNWzgj2iLEI,90631
 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
@@ -332,7 +332,7 @@ alita_sdk/tools/testrail/api_wrapper.py,sha256=tQcGlFJmftvs5ZiO4tsP19fCo4CrJeq_U
 alita_sdk/tools/utils/__init__.py,sha256=xB9OQgW65DftadrSpoAAitnEIbIXZKBOCji0NDe7FRM,3923
 alita_sdk/tools/utils/available_tools_decorator.py,sha256=IbrdfeQkswxUFgvvN7-dyLMZMyXLiwvX7kgi3phciCk,273
 alita_sdk/tools/utils/content_parser.py,sha256=7ohj8HeL_-rmc-Fv0TS8IpxIQC8tOpfuhyT3XlWx-gQ,15368
-alita_sdk/tools/vector_adapters/VectorStoreAdapter.py,sha256=eDezsk41b5ql3CISQ6Xk-qE3foO-PjY0VSWeZnVxHPE,19019
+alita_sdk/tools/vector_adapters/VectorStoreAdapter.py,sha256=Fm-7zKn4RmVER2m0HNiEO7zUDgGKmgCcM8mRaer-2Yw,19025
 alita_sdk/tools/vector_adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 alita_sdk/tools/xray/__init__.py,sha256=eOMWP8VamFbbJgt1xrGpGPqB9ByOTA0Cd3LCaETzGk4,4376
 alita_sdk/tools/xray/api_wrapper.py,sha256=uj5kzUgPdo_Oct9WCNMOpkb6o_3L7J4LZrEGtrwYMmc,30157
@@ -353,8 +353,8 @@ 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-0.3.380.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-alita_sdk-0.3.380.dist-info/METADATA,sha256=81aR6cJaFL6Ez549W3wrMAlKIKG7veu3PsTcEs5rw18,19071
-alita_sdk-0.3.380.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-alita_sdk-0.3.380.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
-alita_sdk-0.3.380.dist-info/RECORD,,
+alita_sdk-0.3.382.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+alita_sdk-0.3.382.dist-info/METADATA,sha256=-Iut0sm4fsmy3rvpKk8q-fPFyzuIvdbBwy6UYkYztAU,19071
+alita_sdk-0.3.382.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+alita_sdk-0.3.382.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
+alita_sdk-0.3.382.dist-info/RECORD,,