alita-sdk 0.3.348__py3-none-any.whl → 0.3.349__py3-none-any.whl

alita_sdk/runtime/langchain/document_loaders/AlitaExcelLoader.py

@@ -201,7 +201,7 @@ class AlitaExcelLoader(AlitaTableLoader):
         return docs
 
     def read(self, lazy: bool = False):
-        df = pd.read_excel(self.file_path, sheet_name=None)
+        df = pd.read_excel(self.file_path, sheet_name=None, engine='calamine')
         docs = []
         for key in df.keys():
             if self.raw_content:
@@ -212,7 +212,7 @@ class AlitaExcelLoader(AlitaTableLoader):
         return docs
 
     def read_lazy(self) -> Iterator[dict]:
-        df = pd.read_excel(self.file_path, sheet_name=None)
+        df = pd.read_excel(self.file_path, sheet_name=None, engine='calamine')
         for key in df.keys():
             if self.raw_content:
                 yield df[key].to_string()

alita_sdk/runtime/langchain/langraph_agent.py

@@ -1,4 +1,5 @@
 import logging
+import re
 from typing import Union, Any, Optional, Annotated, get_type_hints
 from uuid import uuid4
 from typing import Dict
@@ -274,11 +275,20 @@ class StateModifierNode(Runnable):
                 logger.warning(f"Failed to decode base64 value: {e}")
                 return value
         
+        def split_by_words(value, chunk_size=100):
+            words = value.split()
+            return [" ".join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
+        
+        def split_by_regex(value, pattern):
+            """Splits the provided string using the specified regex pattern."""
+            return re.split(pattern, value)
 
         env = Environment()
         env.filters['from_json'] = from_json
-        env.filters['base64ToString'] = base64_to_string
-        
+        env.filters['base64_to_string'] = base64_to_string
+        env.filters['split_by_words'] = split_by_words
+        env.filters['split_by_regex'] = split_by_regex
+
         template = env.from_string(self.template)
         rendered_message = template.render(**input_data)
         result = {}

alita_sdk/runtime/tools/artifact.py

@@ -3,6 +3,7 @@ import logging
 import re
 from typing import Any, Optional, Generator, List
 
+from langchain_core.callbacks import dispatch_custom_event
 from langchain_core.documents import Document
 from langchain_core.tools import ToolException
 from pydantic import create_model, Field, model_validator
@@ -30,7 +31,21 @@ class ArtifactWrapper(NonCodeIndexerToolkit):
         return self.artifact.list(bucket_name, return_as_string)
 
     def create_file(self, filename: str, filedata: str, bucket_name = None):
-        return self.artifact.create(filename, filedata, bucket_name)
+        result = self.artifact.create(filename, filedata, bucket_name)
+        
+        # Dispatch custom event for file creation
+        dispatch_custom_event("file_modified", {
+            "message": f"File '{filename}' created successfully",
+            "filename": filename,
+            "tool_name": "createFile",
+            "toolkit": "artifact",
+            "operation_type": "create",
+            "meta": {
+                "bucket": bucket_name or self.bucket
+            }
+        })
+        
+        return result
 
     def read_file(self,
                   filename: str,
@@ -51,10 +66,38 @@ class ArtifactWrapper(NonCodeIndexerToolkit):
         return self.artifact.delete(filename, bucket_name)
 
     def append_data(self, filename: str, filedata: str, bucket_name = None):
-        return self.artifact.append(filename, filedata, bucket_name)
+        result = self.artifact.append(filename, filedata, bucket_name)
+        
+        # Dispatch custom event for file append
+        dispatch_custom_event("file_modified", {
+            "message": f"Data appended to file '{filename}' successfully",
+            "filename": filename,
+            "tool_name": "appendData",
+            "toolkit": "artifact",
+            "operation_type": "modify",
+            "meta": {
+                "bucket": bucket_name or self.bucket
+            }
+        })
+        
+        return result
 
     def overwrite_data(self, filename: str, filedata: str, bucket_name = None):
-        return self.artifact.overwrite(filename, filedata, bucket_name)
+        result = self.artifact.overwrite(filename, filedata, bucket_name)
+        
+        # Dispatch custom event for file overwrite
+        dispatch_custom_event("file_modified", {
+            "message": f"File '{filename}' overwritten successfully",
+            "filename": filename,
+            "tool_name": "overwriteData",
+            "toolkit": "artifact",
+            "operation_type": "modify",
+            "meta": {
+                "bucket": bucket_name or self.bucket
+            }
+        })
+        
+        return result
 
     def create_new_bucket(self, bucket_name: str, expiration_measure = "weeks", expiration_value = 1):
         return self.artifact.client.create_bucket(bucket_name, expiration_measure, expiration_value)

alita_sdk/tools/base_indexer_toolkit.py

@@ -279,7 +279,8 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         """Cleans the indexed data in the collection."""
         super()._clean_collection(collection_suffix=collection_suffix)
         return (f"Collection '{collection_suffix}' has been removed from the vector store.\n"
-                f"Available collections: {self.list_collections()}")
+                f"Available collections: {self.list_collections()}") if collection_suffix \
+            else "All collections have been removed from the vector store." 
 
     def _build_collection_filter(self, filter: dict | str, collection_suffix: str = "") -> dict:
         """Builds a filter for the collection based on the provided suffix."""

alita_sdk/tools/pandas/api_wrapper.py

@@ -93,7 +93,7 @@ class PandasWrapper(BaseToolApiWrapper):
             if file_extension in ['csv', 'txt']:
                 df = pd.read_csv(file_obj)
             elif file_extension in ['xlsx', 'xls']:
-                df = pd.read_excel(file_obj)
+                df = pd.read_excel(file_obj, engine='calamine')
             elif file_extension == 'parquet':
                 df = pd.read_parquet(file_obj)
             elif file_extension == 'json':
@@ -162,35 +162,17 @@ class PandasWrapper(BaseToolApiWrapper):
         """Analyze and process using query on dataset""" 
         df = self._get_dataframe(filename)
         code = self.generate_code_with_retries(df, query)
-        dispatch_custom_event(
-                name="thinking_step",
-                data={
-                    "message": f"Executing generated code... \n\n```python\n{code}\n```",
-                    "tool_name": "process_query",
-                    "toolkit": "pandas"
-                }
-            )
+        self._log_tool_event(tool_name="process_query",
+                             message=f"Executing generated code... \n\n```python\n{code}\n```")
         try:
             result = self.execute_code(df, code)
         except Exception as e:
             logger.error(f"Code execution failed: {format_exc()}")
-            dispatch_custom_event(
-                name="thinking_step",
-                data={
-                    "message": f"Code execution failed: {format_exc()}",
-                    "tool_name": "process_query",
-                    "toolkit": "pandas"
-                }
-            )
+            self._log_tool_event(tool_name="process_query",
+                                 message=f"Executing generated code... \n\n```python\n{code}\n```")
             raise
-        dispatch_custom_event(
-            name="thinking_step",
-            data={
-                "message": f"Result of code execution... \n\n```\n{result['result']}\n```",
-                "tool_name": "process_query",
-                "toolkit": "pandas"
-            }
-        )
+        self._log_tool_event(tool_name="process_query",
+                             message=f"Executing generated code... \n\n```python\n{code}\n```")
         if result.get("df") is not None:
             df = result.pop("df")
             # Not saving dataframe to artifact repo for now

{alita_sdk-0.3.348.dist-info → alita_sdk-0.3.349.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.348
+Version: 0.3.349
 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
@@ -128,6 +128,7 @@ Requires-Dist: textract-py3==2.1.1; extra == "tools"
 Requires-Dist: slack_sdk==3.35.0; extra == "tools"
 Requires-Dist: deltalake==1.0.2; extra == "tools"
 Requires-Dist: google_cloud_bigquery==3.34.0; extra == "tools"
+Requires-Dist: python-calamine==0.5.3; extra == "tools"
 Provides-Extra: community
 Requires-Dist: retry-extended==0.2.3; extra == "community"
 Requires-Dist: pyobjtojson==0.3; extra == "community"

{alita_sdk-0.3.348.dist-info → alita_sdk-0.3.349.dist-info}/RECORD

@@ -44,7 +44,7 @@ alita_sdk/runtime/langchain/assistant.py,sha256=lF46zxtEg8Tnims5gm-24jvjvUoJ28GB
 alita_sdk/runtime/langchain/chat_message_template.py,sha256=kPz8W2BG6IMyITFDA5oeb5BxVRkHEVZhuiGl4MBZKdc,2176
 alita_sdk/runtime/langchain/constants.py,sha256=eHVJ_beJNTf1WJo4yq7KMK64fxsRvs3lKc34QCXSbpk,3319
 alita_sdk/runtime/langchain/indexer.py,sha256=0ENHy5EOhThnAiYFc7QAsaTNp9rr8hDV_hTK8ahbatk,37592
-alita_sdk/runtime/langchain/langraph_agent.py,sha256=5I5l4zpbKeHy9JONwkkrEyFAMzpBY_BBeAOhHPwmWB8,46866
+alita_sdk/runtime/langchain/langraph_agent.py,sha256=XR6M_MufA0HEtfAESbHfXNU3DF45rh_H8z14wDfs1V8,47339
 alita_sdk/runtime/langchain/mixedAgentParser.py,sha256=M256lvtsL3YtYflBCEp-rWKrKtcY1dJIyRGVv7KW9ME,2611
 alita_sdk/runtime/langchain/mixedAgentRenderes.py,sha256=asBtKqm88QhZRILditjYICwFVKF5KfO38hu2O-WrSWE,5964
 alita_sdk/runtime/langchain/store_manager.py,sha256=i8Fl11IXJhrBXq1F1ukEVln57B1IBe-tqSUvfUmBV4A,2218
@@ -56,7 +56,7 @@ alita_sdk/runtime/langchain/document_loaders/AlitaCSVLoader.py,sha256=3ne-a5qIkB
 alita_sdk/runtime/langchain/document_loaders/AlitaConfluenceLoader.py,sha256=NzpoL4C7UzyzLouTSL_xTQw70MitNt-WZz3Eyl7QkTA,8294
 alita_sdk/runtime/langchain/document_loaders/AlitaDirectoryLoader.py,sha256=fKezkgvIcLG7S2PVJp1a8sZd6C4XQKNZKAFC87DbQts,7003
 alita_sdk/runtime/langchain/document_loaders/AlitaDocxMammothLoader.py,sha256=9hi5eHgDIfa9wBWqTuwMM6D6W64czrDTfZl_htooe8Y,5943
-alita_sdk/runtime/langchain/document_loaders/AlitaExcelLoader.py,sha256=h8x1Xma_IBM4NdGXVVuvHHSlFQgY0S7Xjj8oGZhdFL8,9256
+alita_sdk/runtime/langchain/document_loaders/AlitaExcelLoader.py,sha256=YI8QaHRjCl8WtxuQKMXi_iTJBZ6da3OTNgoDFqNjz1g,9294
 alita_sdk/runtime/langchain/document_loaders/AlitaGitRepoLoader.py,sha256=5WXGcyHraSVj3ANHj_U6X4EDikoekrIYtS0Q_QqNIng,2608
 alita_sdk/runtime/langchain/document_loaders/AlitaImageLoader.py,sha256=QwgBJE-BvOasjgT1hYHZc0MP0F_elirUjSzKixoM6fY,6610
 alita_sdk/runtime/langchain/document_loaders/AlitaJSONLoader.py,sha256=Nav2cgCQKOHQi_ZgYYn_iFdP_Os56KVlVR5nHGXecBc,3445
@@ -106,7 +106,7 @@ alita_sdk/runtime/toolkits/vectorstore.py,sha256=BGppQADa1ZiLO17fC0uCACTTEvPHlod
 alita_sdk/runtime/tools/__init__.py,sha256=7OA8YPKlEOfXu3-gJA08cyR-VymjSPL-OmbXI-B2xVA,355
 alita_sdk/runtime/tools/agent.py,sha256=m98QxOHwnCRTT9j18Olbb5UPS8-ZGeQaGiUyZJSyFck,3162
 alita_sdk/runtime/tools/application.py,sha256=z3vLZODs-_xEEnZFmGF0fKz1j3VtNJxqsAmg5ovExpQ,3129
-alita_sdk/runtime/tools/artifact.py,sha256=4xA_va11WxO0fQclavKivRo24GI1b5qpsp2YZt7RxGY,10795
+alita_sdk/runtime/tools/artifact.py,sha256=wh2e9JSVBZzJHhNOANhHFF6BaK0RtuZ3kvhkqTrTbys,12234
 alita_sdk/runtime/tools/datasource.py,sha256=pvbaSfI-ThQQnjHG-QhYNSTYRnZB0rYtZFpjCfpzxYI,2443
 alita_sdk/runtime/tools/echo.py,sha256=spw9eCweXzixJqHnZofHE1yWiSUa04L4VKycf3KCEaM,486
 alita_sdk/runtime/tools/function.py,sha256=0iZJ-UxaPbtcXAVX9G5Vsn7vmD7lrz3cBG1qylto1gs,2844
@@ -134,7 +134,7 @@ 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=VXNLsdeTmf6snn9EtUyobv4yL-xzLhUcH8P_ORMifYc,675
 alita_sdk/tools/__init__.py,sha256=jUj1ztC2FbkIUB-YYmiqaz_rqW7Il5kWzDPn1mJmj5w,10545
-alita_sdk/tools/base_indexer_toolkit.py,sha256=IKtnJVX27yPu8bBWgbl-5YfUQy4pJPnBoRBFLkqagoc,20228
+alita_sdk/tools/base_indexer_toolkit.py,sha256=hRo93pgb8uJbQgxPle5n7CtLbSbY97jfVq2GKkoNzvc,20328
 alita_sdk/tools/elitea_base.py,sha256=up3HshASSDfjlHV_HPrs1aD4JIwwX0Ug26WGTzgIYvY,34724
 alita_sdk/tools/non_code_indexer_toolkit.py,sha256=B3QvhpT1F9QidkCcsOi3J_QrTOaNlTxqWFwe90VivQQ,1329
 alita_sdk/tools/ado/__init__.py,sha256=NnNYpNFW0_N_v1td_iekYOoQRRB7PIunbpT2f9ZFJM4,1201
@@ -276,7 +276,7 @@ alita_sdk/tools/ocr/api_wrapper.py,sha256=08UF8wj1sR8DcW0z16pw19bgLatLkBF8dySW-D
 alita_sdk/tools/ocr/text_detection.py,sha256=1DBxt54r3_HdEi93QynSIVta3rH3UpIvy799TPtDTtk,23825
 alita_sdk/tools/openapi/__init__.py,sha256=x1U4SGApL6MmNFz9SSsQCv352wMAIdGv0z4eMmYnjCw,4984
 alita_sdk/tools/pandas/__init__.py,sha256=rGenKJH5b9__qM4GerpyLT5YEhNk7W1gA7gn6Zpew04,2748
-alita_sdk/tools/pandas/api_wrapper.py,sha256=froH0h7NPPyFUHWNioESzJ-PQQ522oBM7hNTMfh3qAw,11494
+alita_sdk/tools/pandas/api_wrapper.py,sha256=wn0bagB45Tz_kN0FoKUCIxKcYklMMWTqQP5NOM8_Kwc,11100
 alita_sdk/tools/pandas/dataframe/__init__.py,sha256=iOZRlYDEtwqg2MaYFFxETjN8yHAkUqSNe86cm6ao4LA,108
 alita_sdk/tools/pandas/dataframe/errors.py,sha256=MBzpi5e2p3lNKxiVadzuT5A_DwuTT8cpJ059rXsdabs,320
 alita_sdk/tools/pandas/dataframe/prompts.py,sha256=Zvc-LQ7MifldDTuhxbi-RkpAyO5Gae1wDBtTU6Ygs3k,2884
@@ -350,8 +350,8 @@ 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-0.3.348.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-alita_sdk-0.3.348.dist-info/METADATA,sha256=_oiAJpxGjG23s01B-P41PkJqG1oUgdAgS7QUnlyS5gc,19015
-alita_sdk-0.3.348.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-alita_sdk-0.3.348.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
-alita_sdk-0.3.348.dist-info/RECORD,,
+alita_sdk-0.3.349.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+alita_sdk-0.3.349.dist-info/METADATA,sha256=7-TBm0rWMDR8iCwUI1ixF6841zGe1wyOqfeGEoLkiRU,19071
+alita_sdk-0.3.349.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+alita_sdk-0.3.349.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
+alita_sdk-0.3.349.dist-info/RECORD,,