flowcept 0.9.2__py3-none-any.whl → 0.9.3__py3-none-any.whl

flowcept/agents/flowcept_ctx_manager.py

@@ -53,7 +53,7 @@ class FlowceptAgentContextManager(BaseAgentContextManager):
         Current application context holding task state and QA components.
     msgs_counter : int
         Counter tracking how many task messages have been processed.
-    context_size : int
+    context_chunk_size : int
         Number of task messages to collect before triggering QA index building and LLM analysis.
     qa_manager : FlowceptQAManager
         Utility for constructing QA chains from task summaries.
@@ -64,7 +64,7 @@ class FlowceptAgentContextManager(BaseAgentContextManager):
         self.tracker_config = dict(max_examples=3, max_str_len=50)
         self.schema_tracker = DynamicSchemaTracker(**self.tracker_config)
         self.msgs_counter = 0
-        self.context_size = 1
+        self.context_chunk_size = 1  # Should be in the settings
         super().__init__()
 
     def message_handler(self, msg_obj: Dict):
@@ -98,18 +98,22 @@ class FlowceptAgentContextManager(BaseAgentContextManager):
             if len(task_summary.get("tags", [])):
                 self.context.critical_tasks.append(task_summary)
 
-            if self.msgs_counter > 0 and self.msgs_counter % self.context_size == 0:
+            if self.msgs_counter > 0 and self.msgs_counter % self.context_chunk_size == 0:
                 self.logger.debug(
-                    f"Going to add to index! {(self.msgs_counter - self.context_size, self.msgs_counter)}"
+                    f"Going to add to index! {(self.msgs_counter - self.context_chunk_size, self.msgs_counter)}"
                 )
                 try:
                     self.update_schema_and_add_to_df(
-                        tasks=self.context.task_summaries[self.msgs_counter - self.context_size : self.msgs_counter]
+                        tasks=self.context.task_summaries[
+                            self.msgs_counter - self.context_chunk_size : self.msgs_counter
+                        ]
                     )
                 except Exception as e:
                     self.logger.error(
                         f"Could not add these tasks to buffer!\n"
-                        f"{self.context.task_summaries[self.msgs_counter - self.context_size : self.msgs_counter]}"
+                        f"{
+                            self.context.task_summaries[self.msgs_counter - self.context_chunk_size : self.msgs_counter]
+                        }"
                     )
                     self.logger.exception(e)
 

flowcept/agents/gui/gui_utils.py

@@ -1,3 +1,5 @@
+import base64
+import ast
 import io
 import json
 
@@ -122,6 +124,53 @@ def display_ai_msg_from_tool(tool_result: ToolResult):
     return agent_reply
 
 
+def _sniff_mime(b: bytes) -> str:
+    if b.startswith(b"\x89PNG\r\n\x1a\n"):
+        return "image/png"
+    if b.startswith(b"\xff\xd8\xff"):
+        return "image/jpeg"
+    if b.startswith(b"GIF87a") or b.startswith(b"GIF89a"):
+        return "image/gif"
+    if b.startswith(b"BM"):
+        return "image/bmp"
+    if b.startswith(b"RIFF") and b[8:12] == b"WEBP":
+        return "image/webp"
+    return "application/octet-stream"
+
+
+def ensure_data_uri(val):
+    r"""Accepts bytes/bytearray/memoryview or a repr like \"b'\\x89PNG...'\" and returns a data URL."""
+    if isinstance(val, str) and val.startswith("data:"):
+        return val
+    if isinstance(val, str) and val.startswith("b'"):
+        try:
+            val = ast.literal_eval(val)  # turn repr into bytes
+        except Exception:
+            return None
+    if isinstance(val, memoryview):
+        val = val.tobytes()
+    if isinstance(val, bytearray):
+        val = bytes(val)
+    if isinstance(val, bytes):
+        mime = _sniff_mime(val)
+        return f"data:{mime};base64,{base64.b64encode(val).decode('ascii')}"
+    return val  # path/URL, etc.
+
+
+def _render_df(df: pd.DataFrame, image_width: int = 90, row_height: int = 90):
+    if "image" in df.columns:
+        df = df.copy()
+        df["image"] = df["image"].apply(ensure_data_uri)
+        st.dataframe(
+            df,
+            column_config={"image": st.column_config.ImageColumn("Preview", width=image_width)},
+            hide_index=True,
+            row_height=row_height,  # make thumbnails visible
+        )
+    else:
+        st.dataframe(df, hide_index=True)
+
+
 def display_df_tool_response(tool_result: ToolResult):
     r"""
     Display the DataFrame contained in a ToolResult.
@@ -170,7 +219,8 @@ def display_df_tool_response(tool_result: ToolResult):
             df = pd.read_csv(io.StringIO(result_df_str))
             print("The result is a df")
             if not df.empty:
-                st.dataframe(df, hide_index=False)
+                _render_df(df)
+
                 print("Columns", str(df.columns))
                 print("Number of columns", len(df.columns))
             else:
@@ -190,6 +240,7 @@ def display_df_tool_response(tool_result: ToolResult):
 
         if summary:
             st.markdown("📝 Summary:")
+            print(f"THIS IS THE SUMMARY\n{summary}")
             st.markdown(summary)
         elif summary_error:
             st.markdown(f"⚠️ Encountered this error when summarizing the result dataframe:\n```text\n{summary_error}")

flowcept/agents/prompts/in_memory_query_prompts.py

@@ -15,6 +15,7 @@ COMMON_TASK_FIELDS = """
     | `ended_at`                    | datetime64[ns, UTC] | End time of a task. | 
     | `subtype`                     | string | Subtype of a task. |
     | `tags`                        | List[str] | List of descriptive tags. |
+    | `image`                        | blob | Raw binary data related to an image. |
     | `telemetry_summary.duration_sec` | float | Task duration (seconds). |
     | `telemetry_summary.cpu.percent_all_diff` | float | Difference in overall CPU utilization percentage across all cores between task end and start.|
     | `telemetry_summary.cpu.user_time_diff`   | float |  Difference average per core CPU user time ( seconds ) between task start and end times.|
@@ -27,6 +28,17 @@ COMMON_TASK_FIELDS = """
 DF_FORM = "The user has a pandas DataFrame called `df`, created from flattened task objects using `pd.json_normalize`."
 
 
+def get_example_values_prompt(example_values):
+    values_prompt = f"""    
+           Now, this other dictionary below provides type (t), up to 3 example values (v), and, for lists, shape (s) and element type (et) for each field.
+           Field names do not include `used.` or `generated.` They represent the unprefixed form shared across roles. String values may be truncated if they exceed the length limit.
+           ```python
+           {example_values}
+           ```
+       """
+    return values_prompt
+
+
 def get_df_schema_prompt(dynamic_schema, example_values):
     schema_prompt = f"""
      ## DATAFRAME STRUCTURE
@@ -52,14 +64,7 @@ def get_df_schema_prompt(dynamic_schema, example_values):
         ---
     """
 
-    values_prompt = f"""    
-        Now, this other dictionary below provides type (t), up to 3 example values (v), and, for lists, shape (s) and element type (et) for each field.
-        Field names do not include `used.` or `generated.` They represent the unprefixed form shared across roles. String values may be truncated if they exceed the length limit.
-        ```python
-        {example_values}
-        ```
-    """
-
+    values_prompt = get_example_values_prompt(example_values)
     # values_prompt = ""
     prompt = schema_prompt + values_prompt
     return prompt
@@ -221,7 +226,7 @@ def generate_pandas_code_prompt(query: str, dynamic_schema, example_values):
         f"{JOB}"
         f"{DF_FORM}"
         f"{get_df_schema_prompt(dynamic_schema, example_values)}"  # main tester
-        # f"{QUERY_GUIDELINES}" # main tester
+        f"{QUERY_GUIDELINES}"  # main tester
         f"{FEW_SHOTS}"  # main tester
         f"{OUTPUT_FORMATTING}"
         "User Query:"
@@ -230,9 +235,16 @@ def generate_pandas_code_prompt(query: str, dynamic_schema, example_values):
     return prompt
 
 
-def dataframe_summarizer_context(code, reduced_df, query) -> str:
+def dataframe_summarizer_context(code, reduced_df, dynamic_schema, example_values, query) -> str:
+    job = "You are a Workflow Provenance Specialist analyzing a DataFrame that was obtained to answer a query."
+
+    if "image" in reduced_df.columns:
+        reduced_df = reduced_df.drop(columns=["image"])
+
     prompt = f"""
-    You are a Workflow Provenance Specialist analyzing a DataFrame that was obtained to answer a query. Given:
+    {job}
+    
+     Given:
     
     **User Query**:  
     {query}
@@ -240,19 +252,26 @@ def dataframe_summarizer_context(code, reduced_df, query) -> str:
     **Query_Code**:  
     {code}
     
-    **Reduced DataFrame** (rows sampled from full result):  
+    **Reduced DataFrame `df` contents** (rows sampled from full result):  
     {reduced_df}
     
-    Your task is to:
-    1. Analyze the DataFrame values and columns for any meaningful or notable information.
-    2. Compare the query_code with the data content to understand what the result represents. THIS IS A REDUCED DATAFRAME, the original dataframe, used to answer the query, may be much bigger. IT IS ALREADY KNOWN! Do not need to restate this.
-    3. Provide a concise and direct answer to the user query. Your final response to the query should be  within ```text .
+    **Original df (before reduction) had this schema:
+    {get_df_schema_prompt(dynamic_schema, example_values)}
+    
+    Your task is to find a concise and direct answer as an English sentence to the user query.
+        
+    Only if the answer to the query is complex, provide more explanation by: 
+        1. Analyzing the DataFrame values and columns for any meaningful or notable information. 
+        2. Comparing the query_code with the data content to understand what the result represents. THIS IS A REDUCED DATAFRAME, the original dataframe, used to answer the query, may be much bigger. IT IS ALREADY KNOWN! Do not need to restate this.
+        3. If it makes sense, provide information beyond the recorded provenance, but state it clearly that you are inferring it.
+    
+    In the end, conclude by giving your concise answer as follows: **Response**: <YOUR ANSWER>
 
     Note that the user should not know that this is a reduced dataframe. 
-    
     Keep your response short and focused.
 
     """
+
     return prompt
 
 

flowcept/agents/tools/general_tools.py

@@ -74,7 +74,7 @@ def prompt_handler(message: str) -> ToolResult:
     TextContent
         The AI response or routing feedback.
     """
-    df_key_words = {"save", "result = df", "reset context"}
+    df_key_words = ["df", "save", "result = df", "reset context"]
     for key in df_key_words:
         if key in message:
             return run_df_query(llm=None, query=message, plot=False)

flowcept/agents/tools/in_memory_queries/in_memory_queries_tools.py

@@ -294,6 +294,8 @@ def generate_result_df(llm, query: str, dynamic_schema, example_values, df, atte
     >>> generate_result_df(llm, "bad query", schema, examples, df, attempt_fix=False)
     ToolResult(code=405, result="Failed to parse this as Python code: ...")
     """
+    if llm is None:
+        llm = build_llm_model()
     try:
         prompt = generate_pandas_code_prompt(query, dynamic_schema, example_values)
         response = llm(prompt)
@@ -351,7 +353,14 @@ def generate_result_df(llm, query: str, dynamic_schema, example_values, df, atte
     summary, summary_error = None, None
     if summarize:
         try:
-            tool_result = summarize_result(llm, result_code, result_df, query)
+            tool_result = summarize_result(
+                llm,
+                result_code,
+                result_df,
+                query,
+                dynamic_schema,
+                example_values,
+            )
             if tool_result.is_success():
                 return_code = 301
                 summary = tool_result.result
@@ -570,7 +579,14 @@ def extract_or_fix_json_code(llm, raw_text) -> ToolResult:
 
 
 @mcp_flowcept.tool()
-def summarize_result(llm, code, result, query: str) -> ToolResult:
+def summarize_result(
+    llm,
+    code,
+    result,
+    query: str,
+    dynamic_schema,
+    example_values,
+) -> ToolResult:
     """
     Summarize the pandas result with local reduction for large DataFrames.
     - For wide DataFrames, selects top columns based on variance and uniqueness.
@@ -578,7 +594,7 @@ def summarize_result(llm, code, result, query: str) -> ToolResult:
     - Constructs a detailed prompt for the LLM with original column context.
     """
     summarized_df = summarize_df(result, code)
-    prompt = dataframe_summarizer_context(code, summarized_df, query)
+    prompt = dataframe_summarizer_context(code, summarized_df, dynamic_schema, example_values, query)
     try:
         response = llm(prompt)
         return ToolResult(code=201, result=response)

flowcept/commons/task_data_preprocess.py

@@ -137,7 +137,6 @@ def summarize_task(task: Dict, thresholds: Dict = None, logger=None) -> Dict:
         "agent_id",
         "campaign_id",
         "subtype",
-        "custom_metadata",
     ]:
         value = _safe_get(task, key)
         if value is not None:
@@ -146,7 +145,14 @@ def summarize_task(task: Dict, thresholds: Dict = None, logger=None) -> Dict:
             else:
                 task_summary[key] = value
 
-        # Special handling for timestamp field
+    # Adding image column if data is image. This is to handle special cases when there is an image associated to
+    # a provenance task.
+    if "data" in task:
+        if "custom_metadata" in task:
+            if "image" in task["custom_metadata"].get("mime_type", ""):
+                task_summary["image"] = task["data"]
+
+    # Special handling for timestamp field
     try:
         time_keys = ["started_at", "ended_at"]
         for time_key in time_keys:

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__ = "0.9.2"
+__version__ = "0.9.3"

{flowcept-0.9.2.dist-info → flowcept-0.9.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flowcept
-Version: 0.9.2
+Version: 0.9.3
 Summary: Capture and query workflow provenance data using data observability
 Author: Oak Ridge National Laboratory
 License-Expression: MIT

{flowcept-0.9.2.dist-info → flowcept-0.9.3.dist-info}/RECORD

@@ -1,26 +1,26 @@
 flowcept/__init__.py,sha256=urpwIEJeikV0P6ORXKsM5Lq4o6wCwhySS9A487BYGy4,2241
 flowcept/cli.py,sha256=eVnUrmZtVhZ1ldRMGB1QsqBzNC1Pf2CX33efnlaZ4gs,22842
 flowcept/configs.py,sha256=xw9cdk-bDkR4_bV2jBkDCe9__na9LKJW5tUG32by-m4,8216
-flowcept/version.py,sha256=vKyazpFciSPMlst6m2HH-9RdZcbRHHnKT0jk92I-APc,306
+flowcept/version.py,sha256=p-n2RnT_4VKaEani8rrxiu2EmdHh2opviguHZlI3gso,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
 flowcept/agents/dynamic_schema_tracker.py,sha256=TsmXRRkyUkqB-0bEgmeqSms8xj1tMMJeYvjoaO2mtwI,6829
 flowcept/agents/flowcept_agent.py,sha256=1sidjnNMdG0S6lUKBvml7ZfIb6o3u7zc6HNogsJbl9g,871
-flowcept/agents/flowcept_ctx_manager.py,sha256=-WYulunHE62w61z8cy3u7TEnvgV1hflNEXsnm8YxwFw,6840
+flowcept/agents/flowcept_ctx_manager.py,sha256=8uICi7KDQDbiCYdNSrWGBYQMwwyF3HMbgKY4mPISXuo,7013
 flowcept/agents/gui/__init__.py,sha256=Qw9YKbAzgZqBjMQGnF7XWmfUo0fivtkDISQRK3LA3gU,113
 flowcept/agents/gui/agent_gui.py,sha256=8sTG3MjWBi6oc4tnfHa-duTBXWEE6RBxBE5uHooGkzI,2501
-flowcept/agents/gui/gui_utils.py,sha256=Qex0G9Asgb_UnLTySB8cYNEEy9ZnmLYnLddbornoDcI,7861
+flowcept/agents/gui/gui_utils.py,sha256=61JpFKu-yd7luWVBW6HQYd3feOmupR01tYsZxl804No,9517
 flowcept/agents/llms/__init__.py,sha256=kzOaJic5VhMBnGvy_Fr5C6sRKVrRntH1ZnYz7f5_4-s,23
 flowcept/agents/llms/claude_gcp.py,sha256=fzz7235DgzVueuFj5odsr93jWtYHpYlXkSGW1kmmJwU,4915
 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=q0KmR2QYEtBqQOssoF8W5EhZidqC59wL6XFVjF_dbWQ,3675
-flowcept/agents/prompts/in_memory_query_prompts.py,sha256=oWvZQNUHBBrGq-f94ulhIZW4bkkze02EzAuHY5640QM,17934
+flowcept/agents/prompts/in_memory_query_prompts.py,sha256=o5FXZqaOnIZ9qxlzGN1pT_J7_ZkKQhz0MAD8cVezq-Y,18736
 flowcept/agents/tools/__init__.py,sha256=Xqz2E4-LL_7DDcm1XYJFx2f5RdAsjeTpOJb_DPC7xyc,27
-flowcept/agents/tools/general_tools.py,sha256=Dw1vYNzVUp8dIB48KFPNxGenERoS8UqJj0HIEfhjQeA,2752
+flowcept/agents/tools/general_tools.py,sha256=_S_oCW2xMGc1MAQuy40SHFc3bpmql9v6eH8Nayq4oy8,2758
 flowcept/agents/tools/in_memory_queries/__init__.py,sha256=K8-JI_lXUgquKkgga8Nef8AntGg_logQtjjQjaEE7yI,39
-flowcept/agents/tools/in_memory_queries/in_memory_queries_tools.py,sha256=hrVal1ktf6lvBmVWS7cR_lQy4cIz7ZNYLC-MN61WNRg,25450
+flowcept/agents/tools/in_memory_queries/in_memory_queries_tools.py,sha256=pbwFHmt_vMEGSG4a7tC-KuVRpibkKKf4cbPpQSKAL9w,25736
 flowcept/agents/tools/in_memory_queries/pandas_agent_utils.py,sha256=xi69oywlGb6IUkhQKXoKoswYuWK5FyiWHy2MnRjTzds,9055
 flowcept/analytics/__init__.py,sha256=46q-7vsHq_ddPNrzNnDgEOiRgvlx-5Ggu2ocyROMV0w,641
 flowcept/analytics/analytics_utils.py,sha256=FRJdBtQa7Hrk2oR_FFhmhmMf3X6YyZ4nbH5RIYh7KL4,8753
@@ -31,7 +31,7 @@ flowcept/commons/autoflush_buffer.py,sha256=Ohy_RNbq6BXn0_R83OL5iaTgGPmV8cT1moIR
 flowcept/commons/flowcept_logger.py,sha256=0asRucrDMeRXvsdhuCmH6lWO7lAt_Z5o5uW7rrQhcjc,1857
 flowcept/commons/query_utils.py,sha256=3tyK5VYA10iDtmtzNwa8OQGn93DBxsu6rTjHDphftSc,2208
 flowcept/commons/settings_factory.py,sha256=bMTjgXRfb5HsL2lPnLfem-9trqELbNWE04Ie7lSlxYM,1731
-flowcept/commons/task_data_preprocess.py,sha256=yxLOq3PhfJYDeOUrbBzLc-x7zDrKqB30pwk1nIqtdgo,13552
+flowcept/commons/task_data_preprocess.py,sha256=bJed8Jbo4Mxk6aRVt3sCn4_KxfV5jWXwAIQWwuqHm3U,13846
 flowcept/commons/utils.py,sha256=gF6ENWlTpR2ZSw3yVNPNBTVzSpcgy-WuzYzwWSXXsug,9252
 flowcept/commons/vocabulary.py,sha256=_GzHJ1wSYJlLsu_uu1Am6N3zvc59S4FCuT5yp7lynPw,713
 flowcept/commons/daos/__init__.py,sha256=RO51svfHOg9naN676zuQwbj_RQ6IFHu-RALeefvtwwk,23
@@ -93,9 +93,9 @@ flowcept/instrumentation/flowcept_loop.py,sha256=7hkcolXxbwwccNzoSbAeCCEu02i4zT3
 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=NxiDXh_IAVBsHdxyhB2U-v212hGPLtHTqAVE6_3GyJ0,6756
-flowcept-0.9.2.dist-info/METADATA,sha256=H91pextdVg1DgvI_HPgt4CnRJeH4UmrC5dsZpLwOAiY,31424
-flowcept-0.9.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-flowcept-0.9.2.dist-info/entry_points.txt,sha256=i8q67WE0201rVxYI2lyBtS52shvgl93x2Szp4q8zMlw,47
-flowcept-0.9.2.dist-info/licenses/LICENSE,sha256=r5-2P6tFTuRGWT5TiX32s1y0tnp4cIqBEC1QjTaXe2k,1086
-flowcept-0.9.2.dist-info/RECORD,,
+resources/sample_settings.yaml,sha256=Y2RLR4aZS434yQheN3-lqT1i90vj0YeF3S44Dl_voZM,6756
+flowcept-0.9.3.dist-info/METADATA,sha256=au_dgUmmQMR38AKSb2dL8IEbVhmATxdg3G9y-kF9jOs,31424
+flowcept-0.9.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+flowcept-0.9.3.dist-info/entry_points.txt,sha256=i8q67WE0201rVxYI2lyBtS52shvgl93x2Szp4q8zMlw,47
+flowcept-0.9.3.dist-info/licenses/LICENSE,sha256=r5-2P6tFTuRGWT5TiX32s1y0tnp4cIqBEC1QjTaXe2k,1086
+flowcept-0.9.3.dist-info/RECORD,,

resources/sample_settings.yaml

@@ -1,4 +1,4 @@
-flowcept_version: 0.9.2 # Version of the Flowcept package. This setting file is compatible with this version.
+flowcept_version: 0.9.3 # 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.