flowcept 0.9.7__py3-none-any.whl → 0.9.8__py3-none-any.whl

flowcept/agents/prompts/in_memory_query_prompts.py

@@ -176,6 +176,7 @@ QUERY_GUIDELINES = """
       -To select the first (or earliest) N workflow executions, use or adapt the following: `df.groupby('workflow_id', as_index=False).agg({{"started_at": 'min'}}).sort_values(by='started_at', ascending=True).head(N)['workflow_id']` - utilize `started_at` to sort!     
       -To select the last (or latest or most recent) N workflow executions, use or adapt the following: `df.groupby('workflow_id', as_index=False).agg({{"ended_at": 'max'}}).sort_values(by='ended_at', ascending=False).head(N)['workflow_id']` - utilize `ended_at` to sort!
       
+      -If the user does not ask for a specific workflow run, do not use `workflow_id` in your query. 
       -To select the first or earliest or initial tasks, use or adapt the following: `df.sort_values(by='started_at', ascending=True)`
       -To select the last or final or most recent tasks, use or adapt the following: `df.sort_values(by='ended_at', ascending=False)`
       

flowcept/commons/daos/mq_dao/mq_dao_redis.py

@@ -70,6 +70,7 @@ class MQDaoRedis(MQDao):
                     except Exception as e:
                         self.logger.error(f"Failed to process message {message}")
                         self.logger.exception(e)
+                        continue
 
                     current_trials = 0
             except (redis.exceptions.ConnectionError, redis.exceptions.TimeoutError) as e:
@@ -78,7 +79,7 @@ class MQDaoRedis(MQDao):
                 sleep(3)
             except Exception as e:
                 self.logger.exception(e)
-                break
+                continue
 
     def send_message(self, message: dict, channel=MQ_CHANNEL, serializer=msgpack.dumps):
         """Send the message."""

flowcept/flowcept_api/flowcept_controller.py

@@ -1,7 +1,6 @@
 """Controller module."""
 
-import os.path
-from typing import List, Dict
+from typing import List, Dict, Any
 from uuid import uuid4
 
 from flowcept.commons.autoflush_buffer import AutoflushBuffer
@@ -175,25 +174,31 @@ class Flowcept(object):
         self._interceptor_instances[0]._mq_dao.bulk_publish(self.buffer)
 
     @staticmethod
-    def read_messages_file(file_path: str = None) -> List[Dict]:
+    def read_messages_file(file_path: str | None = None, return_df: bool = False):
         """
         Read a JSON Lines (JSONL) file containing captured Flowcept messages.
 
         This function loads a file where each line is a serialized JSON object.
         It joins the lines into a single JSON array and parses them efficiently
-        with ``orjson``.
+        with ``orjson``. If ``return_df`` is True, it returns a pandas DataFrame
+        created via ``pandas.json_normalize(..., sep='.')`` so nested fields become
+        dot-separated columns (for example, ``generated.attention``).
 
         Parameters
         ----------
         file_path : str, optional
-            Path to the messages file. If not provided, defaults to the
-            value of ``DUMP_BUFFER_PATH`` from the configuration.
-            If neither is provided, an assertion error is raised.
+            Path to the messages file. If not provided, defaults to the value of
+            ``DUMP_BUFFER_PATH`` from the configuration. If neither is provided,
+            an assertion error is raised.
+        return_df : bool, default False
+            If True, return a normalized pandas DataFrame. If False, return the
+            parsed list of dictionaries.
 
         Returns
         -------
-        List[dict]
-            A list of message objects (dictionaries) parsed from the file.
+        list of dict or pandas.DataFrame
+            A list of message objects when ``return_df`` is False,
+            otherwise a normalized DataFrame with dot-separated columns.
 
         Raises
         ------
@@ -203,35 +208,45 @@ class Flowcept(object):
             If the specified file does not exist.
         orjson.JSONDecodeError
             If the file contents cannot be parsed as valid JSON.
+        ModuleNotFoundError
+            If ``return_df`` is True but pandas is not installed.
 
         Examples
         --------
-        Read messages from a file explicitly:
+        Read messages as a list:
 
         >>> msgs = read_messages_file("offline_buffer.jsonl")
-        >>> print(len(msgs))
-        128
+        >>> len(msgs) > 0
+        True
 
-        Use the default dump buffer path from config:
+        Read messages as a normalized DataFrame:
 
-        >>> msgs = read_messages_file()
-        >>> for m in msgs[:2]:
-        ...     print(m["type"], m.get("workflow_id"))
-        task_start wf_123
-        task_end wf_123
+        >>> df = read_messages_file("offline_buffer.jsonl", return_df=True)
+        >>> "generated.attention" in df.columns
+        True
         """
+        import os
         import orjson
 
-        _buffer = []
         if file_path is None:
             file_path = DUMP_BUFFER_PATH
         assert file_path is not None, "Please indicate file_path either in the argument or in the config file."
         if not os.path.exists(file_path):
-            raise f"File {file_path} has not been created. It will only be created if you run in fully offline mode."
+            raise FileNotFoundError(f"File '{file_path}' was not found. It is created only in fully offline mode.")
+
         with open(file_path, "rb") as f:
             lines = [ln for ln in f.read().splitlines() if ln]
-        _buffer = orjson.loads(b"[" + b",".join(lines) + b"]")
-        return _buffer
+
+        buffer: List[Dict[str, Any]] = orjson.loads(b"[" + b",".join(lines) + b"]")
+
+        if return_df:
+            try:
+                import pandas as pd
+            except ModuleNotFoundError as e:
+                raise ModuleNotFoundError("pandas is required when return_df=True. Please install pandas.") from e
+            return pd.json_normalize(buffer, sep=".")
+
+        return buffer
 
     def save_workflow(self, interceptor: str, interceptor_instance: BaseInterceptor):
         """

flowcept/version.py

@@ -4,4 +4,4 @@
 # The expected format is: <Major>.<Minor>.<Patch>
 # This file is supposed to be automatically modified by the CI Bot.
 # See .github/workflows/version_bumper.py
-__version__ = "0.9.7"
+__version__ = "0.9.8"

{flowcept-0.9.7.dist-info → flowcept-0.9.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flowcept
-Version: 0.9.7
+Version: 0.9.8
 Summary: Capture and query workflow provenance data using data observability
 Author: Oak Ridge National Laboratory
 License-Expression: MIT
@@ -27,6 +27,7 @@ Requires-Dist: jupyterlab; extra == 'all'
 Requires-Dist: langchain-community; extra == 'all'
 Requires-Dist: langchain-openai; extra == 'all'
 Requires-Dist: lmdb; extra == 'all'
+Requires-Dist: matplotlib; extra == 'all'
 Requires-Dist: mcp[cli]; extra == 'all'
 Requires-Dist: mlflow-skinny; extra == 'all'
 Requires-Dist: nbmake; extra == 'all'
@@ -88,6 +89,7 @@ Requires-Dist: confluent-kafka<=2.8.0; extra == 'kafka'
 Provides-Extra: llm-agent
 Requires-Dist: langchain-community; extra == 'llm-agent'
 Requires-Dist: langchain-openai; extra == 'llm-agent'
+Requires-Dist: matplotlib; extra == 'llm-agent'
 Requires-Dist: mcp[cli]; extra == 'llm-agent'
 Requires-Dist: pymupdf; extra == 'llm-agent'
 Requires-Dist: streamlit; extra == 'llm-agent'
@@ -95,6 +97,7 @@ Provides-Extra: llm-agent-audio
 Requires-Dist: gtts; extra == 'llm-agent-audio'
 Requires-Dist: langchain-community; extra == 'llm-agent-audio'
 Requires-Dist: langchain-openai; extra == 'llm-agent-audio'
+Requires-Dist: matplotlib; extra == 'llm-agent-audio'
 Requires-Dist: mcp[cli]; extra == 'llm-agent-audio'
 Requires-Dist: pydub; extra == 'llm-agent-audio'
 Requires-Dist: pymupdf; extra == 'llm-agent-audio'
@@ -105,6 +108,7 @@ Provides-Extra: llm-google
 Requires-Dist: google-genai; extra == 'llm-google'
 Requires-Dist: langchain-community; extra == 'llm-google'
 Requires-Dist: langchain-openai; extra == 'llm-google'
+Requires-Dist: matplotlib; extra == 'llm-google'
 Requires-Dist: mcp[cli]; extra == 'llm-google'
 Requires-Dist: pymupdf; extra == 'llm-google'
 Requires-Dist: streamlit; extra == 'llm-google'

{flowcept-0.9.7.dist-info → flowcept-0.9.8.dist-info}/RECORD

@@ -1,7 +1,7 @@
 flowcept/__init__.py,sha256=urpwIEJeikV0P6ORXKsM5Lq4o6wCwhySS9A487BYGy4,2241
 flowcept/cli.py,sha256=eVnUrmZtVhZ1ldRMGB1QsqBzNC1Pf2CX33efnlaZ4gs,22842
 flowcept/configs.py,sha256=aXgBkBpTs4_4MpvAe76aQ5lXl1gTmgk92bFiNqMQXPM,8382
-flowcept/version.py,sha256=82O8Nb-xrNpDOjABeIhhxyF9hYDKXZ1hFjdTCo4zE2Y,306
+flowcept/version.py,sha256=zH7JKitqQGm2p8zaw6JClXGAc-kbLbhXB70bFMI-zhU,306
 flowcept/agents/__init__.py,sha256=8eeD2CiKBtHiDsWdrHK_UreIkKlTq4dUbhHDyzw372o,175
 flowcept/agents/agent_client.py,sha256=UiBQkC9WE2weLZR2OTkEOEQt9-zqQOkPwRA17HfI-jk,2027
 flowcept/agents/agents_utils.py,sha256=Az5lvWTsBHs_3sWWwy7jSdDjNn-PvZ7KmYd79wxvdyU,6666
@@ -17,7 +17,7 @@ flowcept/agents/llms/claude_gcp.py,sha256=fzz7235DgzVueuFj5odsr93jWtYHpYlXkSGW1k
 flowcept/agents/llms/gemini25.py,sha256=VARrjb3tITIh3_Wppmocp_ocSKVZNon0o0GeFEwTnTI,4229
 flowcept/agents/prompts/__init__.py,sha256=7ICsNhLYzvPS1esG3Vg519s51b1c4yN0WegJUb6Qvww,26
 flowcept/agents/prompts/general_prompts.py,sha256=Mj6dMdrnJfq-bibi1XQVNZ8zx5MZUwxTvYY_qijPfoI,3894
-flowcept/agents/prompts/in_memory_query_prompts.py,sha256=j5lZLuQdGzKFRiYaNrNThMwHslPUWwDARdufmFxMoTQ,19562
+flowcept/agents/prompts/in_memory_query_prompts.py,sha256=0u6hIV1v-Fhk3dQVvbEW0qggi0KZbEBopMvJtgCNIVc,19664
 flowcept/agents/tools/__init__.py,sha256=Xqz2E4-LL_7DDcm1XYJFx2f5RdAsjeTpOJb_DPC7xyc,27
 flowcept/agents/tools/general_tools.py,sha256=KS7ZTf1UbTxg0yQ6zCxh1g3NzcliYKWdurMArhPowxs,3248
 flowcept/agents/tools/in_memory_queries/__init__.py,sha256=K8-JI_lXUgquKkgga8Nef8AntGg_logQtjjQjaEE7yI,39
@@ -46,7 +46,7 @@ flowcept/commons/daos/mq_dao/__init__.py,sha256=Xxm4FmbBUZDQ7XIAmSFbeKE_AdHsbgFm
 flowcept/commons/daos/mq_dao/mq_dao_base.py,sha256=EL8eQedvNLsVLMz4oHemBAsR1S6xFZiezM8dIqKmmCA,9696
 flowcept/commons/daos/mq_dao/mq_dao_kafka.py,sha256=kjZqPLIu5PaNeM4IDvOxkDRVGTd5UWwq3zhDvVirqW8,5067
 flowcept/commons/daos/mq_dao/mq_dao_mofka.py,sha256=tRdMGYDzdeIJxad-B4-DE6u8Wzs61eTzOW4ojZrnTxs,4057
-flowcept/commons/daos/mq_dao/mq_dao_redis.py,sha256=WKPoMPBSce4shqbBkgsnuqJAJoZZ4U_hdebhyFqtejQ,5535
+flowcept/commons/daos/mq_dao/mq_dao_redis.py,sha256=ejBMxImA-h2KuMEAk3l7aU0chCcObCbUXEOXM6L4Zhc,5571
 flowcept/commons/flowcept_dataclasses/__init__.py,sha256=8KkiJh0WSRAB50waVluxCSI8Tb9X1L9nup4c8RN3ulc,30
 flowcept/commons/flowcept_dataclasses/base_settings_dataclasses.py,sha256=Cjw2PGYtZDfnwecz6G3S42Ncmxj7AIZVEBx05bsxRUo,399
 flowcept/commons/flowcept_dataclasses/task_object.py,sha256=XLFD8YTWsyDLSRcgZc5qK2a9yk97XnqZoUAL4T6HNPE,8110
@@ -54,7 +54,7 @@ flowcept/commons/flowcept_dataclasses/telemetry.py,sha256=9_5ONCo-06r5nKHXmi5HfI
 flowcept/commons/flowcept_dataclasses/workflow_object.py,sha256=cauWtXHhBv9lHS-q6cb7yUsNiwQ6PkZPuSinR1TKcqU,6161
 flowcept/flowcept_api/__init__.py,sha256=T1ty86YlocQ5Z18l5fUqHj_CC6Unq_iBv0lFyiI7Ao8,22
 flowcept/flowcept_api/db_api.py,sha256=hKXep-n50rp9cAzV0ljk2QVEF8O64yxi3ujXv5_Ibac,9723
-flowcept/flowcept_api/flowcept_controller.py,sha256=JcUQXJfEjmg-KQsolIN5Ul7vbSxZUg8QTWaGAahZKTE,15251
+flowcept/flowcept_api/flowcept_controller.py,sha256=jfssXUvG55RVXJBziq-lXekt7Dog3mAalo5Zsp_7_to,16060
 flowcept/flowcept_api/task_query_api.py,sha256=SrwB0OCVtbpvCPECkE2ySM10G_g8Wlk5PJ8h-0xEaNc,23821
 flowcept/flowcept_webserver/__init__.py,sha256=8411GIXGddKTKoHUvbo_Rq6svosNG7tG8VzvUEBd7WI,28
 flowcept/flowcept_webserver/app.py,sha256=VUV8_JZbIbx9u_1O7m7XtRdhZb_7uifUa-iNlPhmZws,658
@@ -94,9 +94,9 @@ flowcept/instrumentation/flowcept_loop.py,sha256=jea_hYPuXg5_nOWf-nNb4vx8A__OBM4
 flowcept/instrumentation/flowcept_task.py,sha256=EmKODpjl8usNklKSVmsKYyCa6gC_QMqKhAr3DKaw44s,8199
 flowcept/instrumentation/flowcept_torch.py,sha256=kkZQRYq6cDBpdBU6J39_4oKRVkhyF3ODlz8ydV5WGKw,23455
 flowcept/instrumentation/task_capture.py,sha256=1g9EtLdqsTB0RHsF-eRmA2Xh9l_YqTd953d4v89IC24,8287
-resources/sample_settings.yaml,sha256=bOyHdzQe-CJ7nmpqstlDfk9fuQMHerS95Oy2BGdMLds,6779
-flowcept-0.9.7.dist-info/METADATA,sha256=gy3Ul7p8x8MSFq17wOuUtuLMzZay4no0-yFmfEl_Ni0,32246
-flowcept-0.9.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-flowcept-0.9.7.dist-info/entry_points.txt,sha256=i8q67WE0201rVxYI2lyBtS52shvgl93x2Szp4q8zMlw,47
-flowcept-0.9.7.dist-info/licenses/LICENSE,sha256=r5-2P6tFTuRGWT5TiX32s1y0tnp4cIqBEC1QjTaXe2k,1086
-flowcept-0.9.7.dist-info/RECORD,,
+resources/sample_settings.yaml,sha256=ufx-07gm7u0UMJa_HPutD3w1VrZKaPBht5H1xFUbIWU,6779
+flowcept-0.9.8.dist-info/METADATA,sha256=-a_76ZRJ8DAu_cwGtwiW4OIUdil-orVS7TC5heM-Yco,32439
+flowcept-0.9.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+flowcept-0.9.8.dist-info/entry_points.txt,sha256=i8q67WE0201rVxYI2lyBtS52shvgl93x2Szp4q8zMlw,47
+flowcept-0.9.8.dist-info/licenses/LICENSE,sha256=r5-2P6tFTuRGWT5TiX32s1y0tnp4cIqBEC1QjTaXe2k,1086
+flowcept-0.9.8.dist-info/RECORD,,

resources/sample_settings.yaml

@@ -1,4 +1,4 @@
-flowcept_version: 0.9.7 # Version of the Flowcept package. This setting file is compatible with this version.
+flowcept_version: 0.9.8 # Version of the Flowcept package. This setting file is compatible with this version.
 
 project:
   debug: true # Toggle debug mode. This will add a property `debug: true` to all saved data, making it easier to retrieve/delete them later.