flowcept 0.9.6__py3-none-any.whl → 0.9.8__py3-none-any.whl

flowcept/agents/gui/agent_gui.py

@@ -1,76 +1,87 @@
 import streamlit as st
+
 from flowcept.agents.gui import AI, PAGE_TITLE
+from flowcept.agents.gui.audio_utils import get_audio_text
 from flowcept.agents.gui.gui_utils import (
     query_agent,
     display_ai_msg,
     display_ai_msg_from_tool,
     display_df_tool_response,
+    resolve_logo_path,
+    render_title_with_logo,
 )
-
 from flowcept.agents.tools.in_memory_queries.in_memory_queries_tools import (
     generate_result_df,
     generate_plot_code,
     run_df_code,
 )
+from flowcept.configs import AGENT_AUDIO
 
+# ---- Page setup & header with logo ----
 st.set_page_config(page_title=PAGE_TITLE, page_icon=AI)
-st.title(PAGE_TITLE)
+
+LOGO_PATH = resolve_logo_path(package="flowcept", resource="docs/img/flowcept-logo.png")
+render_title_with_logo(PAGE_TITLE, LOGO_PATH, logo_width=150, add_to_sidebar=False, debug=False)
 
 GREETING = (
-    "Hi, there! I'm a **Workflow Provenance Specialist**.\n\n"
+    "Hi, there! I'm your **Workflow Provenance Assistant**.\n\n"
     "I am tracking workflow executions and I can:\n"
-    "- 🔍 Analyze running workflows\n"
+    "- 🔍 Query running workflows\n"
     "- 📊 Plot graphs\n"
     "- 🤖 Answer general questions about provenance data\n\n"
     "How can I help you today?"
 )
-
-
 display_ai_msg(GREETING)
 
-# if "chat_history" not in st.session_state:
-#     st.session_state.chat_history = [{"role": "system", "content":GREETING}]
-#
-# for msg in st.session_state.chat_history:
-#     with st.chat_message(msg["role"], avatar=AI):
-#         st.markdown(msg["content"])
-
 
 def main():
-    """Main Streamlit Function."""
+    """Main Agent GUI function."""
+    st.caption(
+        "💡 Tip: Ask about workflow metrics, generate plots, or summarize data. "
+        "Inputs are mapped to `used` and outputs to `generated` fields. "
+        "Use @record <your query guidance> if you have custom guidance."
+    )
+
     user_input = st.chat_input("Send a message")
-    st.caption("💡 Tip: Ask about workflow metrics, generate plots, or summarize data.")
 
     if user_input:
-        # st.session_state.chat_history.append({"role": "human", "content": user_input})
+        st.session_state["speak_reply"] = False
+
+    if AGENT_AUDIO:
+        user_input = get_audio_text(user_input)
 
+    if user_input:
         with st.chat_message("human"):
             st.markdown(user_input)
 
         try:
             with st.spinner("🤖 Thinking..."):
                 tool_result = query_agent(user_input)
-            print(tool_result)
 
             if tool_result.result_is_str():
                 display_ai_msg_from_tool(tool_result)
+
             elif tool_result.is_success_dict():
                 tool_name = tool_result.tool_name
-                if tool_name in [generate_result_df.__name__, generate_plot_code.__name__, run_df_code.__name__]:
+                if tool_name in (
+                    generate_result_df.__name__,
+                    generate_plot_code.__name__,
+                    run_df_code.__name__,
+                ):
                     display_df_tool_response(tool_result)
                 else:
                     display_ai_msg(f"⚠️ Received unexpected response from agent: {tool_result}")
                     st.stop()
             else:
                 display_df_tool_response(tool_result)
-                # display_ai_msg(f"⚠️ Received unexpected response from agent: {tool_result}")
                 st.stop()
 
         except Exception as e:
             display_ai_msg(f"❌ Error talking to MCP agent:\n\n```text\n{e}\n```")
             st.stop()
 
-        # st.session_state.chat_history.append({"role": "system", "content": agent_reply})
 
+if "speak_reply" not in st.session_state:
+    st.session_state["speak_reply"] = False
 
 main()

flowcept/agents/gui/audio_utils.py

@@ -0,0 +1,129 @@
+import re
+import tempfile
+from io import BytesIO
+import base64
+
+import streamlit as st
+from gtts import gTTS
+from streamlit_mic_recorder import mic_recorder
+import speech_recognition as sr
+from pydub import AudioSegment  # needs ffmpeg installed
+
+
+def _normalize_mic_output(out) -> bytes | None:
+    """Handle different return shapes from streamlit-mic-recorder."""
+    if not isinstance(out, dict):
+        return None
+    if out.get("wav"):
+        return out["wav"]
+    if out.get("bytes"):
+        return out["bytes"]
+    if out.get("b64"):
+        return base64.b64decode(out["b64"])
+    return None
+
+
+def _is_wav_pcm(blob: bytes) -> bool:
+    """Quick RIFF/WAVE header check."""
+    h = blob[:12]
+    return h.startswith(b"RIFF") and h[8:12] == b"WAVE"
+
+
+def _to_pcm_wav_16k(blob: bytes) -> bytes:
+    """
+    Convert arbitrary audio bytes (webm/ogg/mp3/…) to 16-bit PCM WAV mono @16k.
+    Requires ffmpeg via pydub.
+    """
+    if _is_wav_pcm(blob):
+        return blob
+    seg = AudioSegment.from_file(BytesIO(blob))  # ffmpeg does the heavy lifting
+    seg = seg.set_channels(1).set_frame_rate(16000).set_sample_width(2)
+    buf = BytesIO()
+    seg.export(buf, format="wav")
+    return buf.getvalue()
+
+
+def get_audio_text(user_input: str) -> str:
+    """
+    User Audio Getter.
+    """
+    # Voice input expander
+    with st.expander("🎤 Voice input", expanded=False):
+        st.caption("Click **Speak**, talk, then **Stop**. Allow mic permission in your browser.")
+        out = mic_recorder(
+            start_prompt="🎙️ Speak",
+            stop_prompt="⏹️ Stop",
+            key="mic_rec_1",
+            use_container_width=True,
+        )
+
+        # Normalize outputs from the component
+        raw_audio = _normalize_mic_output(out)
+
+        if raw_audio:
+            try:
+                wav_bytes = _to_pcm_wav_16k(raw_audio)
+            except Exception as e:
+                st.error(f"Could not convert audio to WAV (need ffmpeg/ffprobe?): {e}")
+                wav_bytes = None
+
+            if wav_bytes:
+                st.audio(wav_bytes, format="audio/wav")
+
+                # Transcribe with SpeechRecognition
+                r = sr.Recognizer()
+                try:
+                    with sr.AudioFile(BytesIO(wav_bytes)) as source:
+                        audio = r.record(source)
+                    voice_text = r.recognize_google(audio)  # type: ignore[attr-defined]
+                    st.success(f"You said: {voice_text}")
+                    if not user_input:
+                        user_input = voice_text
+                        st.session_state["speak_reply"] = True  # speak back only when voice was used
+                        print(f"Setting session state to {st.session_state['speak_reply']}")
+                except Exception as e:
+                    st.warning(f"Transcription failed: {e}")
+
+    return user_input
+
+
+def speech_to_text():
+    """Record from mic, return transcribed text or None."""
+    rec = mic_recorder(
+        start_prompt="🎙️ Speak",
+        stop_prompt="⏹️ Stop",
+        key="mic",
+        use_container_width=True,
+    )
+    if rec and "wav" in rec:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
+            tmp.write(rec["wav"])
+            tmp.flush()
+            r = sr.Recognizer()
+            with sr.AudioFile(tmp.name) as source:
+                audio = r.record(source)
+            try:
+                return r.recognize_google(audio)
+            except Exception as e:
+                st.warning(f"Speech recognition failed: {e}")
+    return None
+
+
+def speak(text: str):
+    """Synthesize speech for the agent reply and play it."""
+    if not text:
+        return
+    try:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp:
+            gTTS(text).save(tmp.name)
+            st.audio(tmp.name, format="audio/mp3")
+    except Exception as e:
+        st.warning(f"TTS failed: {e}")
+
+
+def _md_to_plain_text(s: str) -> str:
+    """Very light Markdown cleanup for TTS."""
+    s = re.sub(r"```.*?```", lambda m: m.group(0).replace("```", ""), s, flags=re.S)  # drop fences
+    s = s.replace("`", "")  # inline code ticks
+    s = re.sub(r"\[([^\]]+)\]\([^)]+\)", r"\1", s)  # links: [text](url) -> text
+    return s.strip()

flowcept/agents/gui/gui_utils.py

@@ -2,14 +2,20 @@ import base64
 import ast
 import io
 import json
+from pathlib import Path
+from importlib.resources import files as pkg_files
+
+import pandas as pd
 
 import streamlit as st
+from flowcept.agents.gui import AI
 from flowcept.agents import prompt_handler
 from flowcept.agents.agent_client import run_tool
 from flowcept.agents.agents_utils import ToolResult
-import pandas as pd
 
-from flowcept.agents.gui import AI
+
+from flowcept.agents.gui.audio_utils import _md_to_plain_text, speak
+from flowcept.configs import AGENT_AUDIO
 
 
 def query_agent(user_input: str) -> ToolResult:
@@ -125,6 +131,8 @@ def display_ai_msg_from_tool(tool_result: ToolResult):
 
 
 def _sniff_mime(b: bytes) -> str:
+    if b.startswith(b"%PDF-"):
+        return "application/pdf"
     if b.startswith(b"\x89PNG\r\n\x1a\n"):
         return "image/png"
     if b.startswith(b"\xff\xd8\xff"):
@@ -138,23 +146,72 @@ def _sniff_mime(b: bytes) -> str:
     return "application/octet-stream"
 
 
+def _pdf_first_page_to_png(pdf_bytes: bytes, zoom: float = 2.0) -> bytes:
+    """
+    Convert the first page of a PDF to PNG bytes using PyMuPDF (fitz).
+    zoom ~2.0 gives a good thumbnail; increase for higher resolution.
+    """
+    try:
+        import fitz  # PyMuPDF
+    except Exception as e:
+        # PyMuPDF not installed; caller can decide how to handle
+        raise ImportError("PyMuPDF (fitz) is required to render PDF thumbnails") from e
+
+    doc = fitz.open(stream=pdf_bytes, filetype="pdf")
+    try:
+        page = doc.load_page(0)
+        pix = page.get_pixmap(matrix=fitz.Matrix(zoom, zoom), alpha=False)
+        return pix.tobytes("png")
+    finally:
+        doc.close()
+
+
 def ensure_data_uri(val):
-    r"""Accepts bytes/bytearray/memoryview or a repr like \"b'\\x89PNG...'\" and returns a data URL."""
+    r"""Accept bytes/bytearray/memoryview or a repr like "b'\x89PNG...'", or a file path/URL.
+    Returns a data URL suitable for st.column_config.ImageColumn. If input is a PDF, converts
+    the first page to PNG (requires PyMuPDF).
+    """
+    # Already a data URI?
     if isinstance(val, str) and val.startswith("data:"):
         return val
+
+    # Bytes repr string? -> real bytes
     if isinstance(val, str) and val.startswith("b'"):
         try:
-            val = ast.literal_eval(val)  # turn repr into bytes
+            val = ast.literal_eval(val)
         except Exception:
             return None
+
+    # Paths that point to a PDF: convert
+    if isinstance(val, str) and val.lower().endswith(".pdf") and Path(val).is_file():
+        try:
+            pdf_bytes = Path(val).read_bytes()
+            png_bytes = _pdf_first_page_to_png(pdf_bytes)
+            return f"data:image/png;base64,{base64.b64encode(png_bytes).decode('ascii')}"
+        except Exception:
+            # Fallback: no preview; caller will show blank cell
+            return None
+
+    # Normalize to bytes if memoryview/bytearray
     if isinstance(val, memoryview):
         val = val.tobytes()
     if isinstance(val, bytearray):
         val = bytes(val)
+
+    # Raw bytes? detect and convert if PDF
     if isinstance(val, bytes):
         mime = _sniff_mime(val)
+        if mime == "application/pdf":
+            try:
+                png_bytes = _pdf_first_page_to_png(val)
+                return f"data:image/png;base64,{base64.b64encode(png_bytes).decode('ascii')}"
+            except Exception:
+                return None
+        # Regular image bytes -> data URI
         return f"data:{mime};base64,{base64.b64encode(val).decode('ascii')}"
-    return val  # path/URL, etc.
+
+    # Otherwise (URL/path to an image) let Streamlit try; PDFs won’t render as images
+    return val
 
 
 def _render_df(df: pd.DataFrame, image_width: int = 90, row_height: int = 90):
@@ -242,6 +299,17 @@ def display_df_tool_response(tool_result: ToolResult):
             st.markdown("📝 Summary:")
             print(f"THIS IS THE SUMMARY\n{summary}")
             st.markdown(summary)
+
+            if AGENT_AUDIO:
+                # 🔊 Speak only if user spoke to us this turn
+                print(f"This is the session state nowww: {st.session_state['speak_reply']}")
+                if st.session_state.get("speak_reply"):
+                    try:
+                        plain_text = _md_to_plain_text(summary)
+                        print(f"Trying to speak plain text {plain_text}")
+                        speak(plain_text)  # uses your existing gTTS-based speak()
+                    except Exception as e:
+                        st.warning(f"TTS failed: {e}")
         elif summary_error:
             st.markdown(f"⚠️ Encountered this error when summarizing the result dataframe:\n```text\n{summary_error}")
 
@@ -288,3 +356,87 @@ def exec_st_plot_code(code, result_df, st_module):
         code,
         {"result": result_df, "st": st_module, "plt": __import__("matplotlib.pyplot"), "alt": __import__("altair")},
     )
+
+
+def _resolve_logo() -> str | None:
+    # Try package resource
+    try:
+        p = pkg_files("flowcept").joinpath("docs/img/flowcept-logo.png")
+        if p.is_file():
+            return str(p)
+    except Exception:
+        pass
+    # Fallbacks for dev checkouts
+    here = Path(__file__).resolve()
+    candidates = [
+        here.parents[3] / "docs/img/flowcept-logo.png",
+        here.parents[2] / "docs/img/flowcept-logo.png",
+        here.parents[1] / "docs/img/flowcept-logo.png",
+        Path("flowcept/docs/img/flowcept-logo.png"),
+    ]
+    for c in candidates:
+        if c.is_file():
+            return str(c)
+    print(str(c))
+    return None
+
+
+def resolve_logo_path(package: str = "flowcept", resource: str = "docs/img/flowcept-logo.png") -> str | None:
+    """
+    Resolve the Flowcept logo whether running from an installed package or a src/ layout repo.
+    Returns an absolute string path or None if not found.
+    """
+    # 1) Try packaged resource (works if docs/img is included in the wheel/sdist)
+    try:
+        p = pkg_files(package).joinpath(resource)
+        if hasattr(p, "is_file") and p.is_file():
+            return str(p)
+    except Exception:
+        pass
+
+    here = Path(__file__).resolve()
+
+    # 2) src/ layout repo: .../<repo>/flowcept/src/flowcept/agents/gui/gui_utils.py
+    #    Find the nearest 'src' ancestor, then go to repo root (src/..), then docs/img/...
+    try:
+        src_dir = next(p for p in here.parents if p.name == "src")
+        repo_root = src_dir.parent  # <repo>/flowcept
+        cand = repo_root / "docs" / "img" / "flowcept-logo.png"
+        if cand.is_file():
+            return str(cand)
+    except StopIteration:
+        pass
+
+    # 3) Editable install package dir: .../src/flowcept (package root)
+    pkg_dir = here.parents[2]  # .../src/flowcept
+    cand = pkg_dir / "docs" / "img" / "flowcept-logo.png"
+    if cand.is_file():
+        return str(cand)
+
+    # 4) CWD fallback
+    cand = Path.cwd() / "flowcept" / "docs" / "img" / "flowcept-logo.png"
+    if cand.is_file():
+        return str(cand)
+
+    return None
+
+
+def render_title_with_logo(
+    page_title: str, logo_path: str | None, logo_width: int = 150, add_to_sidebar: bool = True, debug: bool = False
+):
+    """
+    Render a header row with an optional logo next to the title; optionally mirror it in the sidebar.
+    """
+    if debug:
+        st.caption(f"Logo path resolved to: {logo_path or 'NOT FOUND'}")
+
+    if logo_path and Path(logo_path).is_file():
+        col_logo, col_title = st.columns([1, 6])
+        with col_logo:
+            st.image(logo_path, width=logo_width)
+        with col_title:
+            st.title(page_title)
+        if add_to_sidebar:
+            st.sidebar.image(logo_path, width=logo_width)
+    else:
+        st.title(page_title)

flowcept/agents/prompts/general_prompts.py

@@ -24,9 +24,9 @@ ROUTING_PROMPT = (
     "Given the following user message, classify it into one of the following routes:\n"
     "- small_talk: if it's casual conversation or some random word (e.g., 'hausdn', 'a', hello, how are you, what can you do, what's your name)\n"
     "- plot: if user is requesting plots (e.g., plot, chart, visualize)\n"
-    #"- in_context_query: if the user asks questions about tasks or data in running workflow (or a workflow that ran recently) or if the user mentions the in-memory 'df' or a dataframe.\n"
+    # "- in_context_query: if the user asks questions about tasks or data in running workflow (or a workflow that ran recently) or if the user mentions the in-memory 'df' or a dataframe.\n"
     "- in_context_query: if the user is querying the provenance data questions about tasks or data in running workflow (or a workflow that ran recently) or if the user mentions the in-memory 'df' or a dataframe.\n"
-    #"- historical_prov_query: if the user wants to query historical provenance data\n"
+    # "- historical_prov_query: if the user wants to query historical provenance data\n"
     "- in_chat_query: if the user appears to be asking about something that has said recently in this chat.\n"
     "- unknown: if you don't know.\n"
     "Respond with only the route label."

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)`
       
@@ -226,10 +227,11 @@ OUTPUT_FORMATTING = """
 def generate_pandas_code_prompt(query: str, dynamic_schema, example_values, custom_user_guidances):
     if custom_user_guidances is not None and isinstance(custom_user_guidances, list) and len(custom_user_guidances):
         concatenated_guidance = "\n".join(f"- {msg}" for msg in custom_user_guidances)
-        custom_user_guidance_prompt = (f"You MUST consider the following guidance from the user:\n"
-                                       f"{concatenated_guidance}"
-                                       "------------------------------------------------------"
-                                       )
+        custom_user_guidance_prompt = (
+            f"You MUST consider the following guidance from the user:\n"
+            f"{concatenated_guidance}"
+            "------------------------------------------------------"
+        )
     else:
         custom_user_guidance_prompt = ""
     prompt = (

flowcept/agents/tools/general_tools.py

@@ -62,6 +62,9 @@ def check_llm() -> str:
 
 @mcp_flowcept.tool()
 def record_guidance(message: str) -> ToolResult:
+    """
+    Record guidance tool.
+    """
     ctx = mcp_flowcept.get_context()
     message = message.replace("@record", "")
     custom_guidance: List = ctx.request_context.lifespan_context.custom_guidance

flowcept/agents/tools/in_memory_queries/in_memory_queries_tools.py

@@ -222,7 +222,9 @@ def generate_plot_code(llm, query, dynamic_schema, value_examples, df, custom_us
 
 
 @mcp_flowcept.tool()
-def generate_result_df(llm, query: str, dynamic_schema, example_values, df, custom_user_guidance=None, attempt_fix=True, summarize=True):
+def generate_result_df(
+    llm, query: str, dynamic_schema, example_values, df, custom_user_guidance=None, attempt_fix=True, summarize=True
+):
     """
     Generate a result DataFrame from a natural language query using an LLM.
 

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/commons/task_data_preprocess.py

@@ -149,7 +149,8 @@ def summarize_task(task: Dict, thresholds: Dict = None, logger=None) -> Dict:
     # a provenance task.
     if "data" in task:
         if "custom_metadata" in task:
-            if "image" in task["custom_metadata"].get("mime_type", ""):
+            mime_type = task["custom_metadata"].get("mime_type", "")
+            if "image" in mime_type or "application/pdf" in mime_type:
                 task_summary["image"] = task["data"]
 
     # Special handling for timestamp field

flowcept/configs.py

@@ -235,6 +235,13 @@ INSTRUMENTATION = settings.get("instrumentation", {})
 INSTRUMENTATION_ENABLED = INSTRUMENTATION.get("enabled", True)
 
 AGENT = settings.get("agent", {})
+AGENT_AUDIO = os.getenv("AGENT_AUDIO", str(settings["agent"].get("audio_enabled", "false"))).strip().lower() in {
+    "1",
+    "true",
+    "yes",
+    "y",
+    "t",
+}
 AGENT_HOST = os.getenv("AGENT_HOST", settings["agent"].get("mcp_host", "localhost"))
 AGENT_PORT = int(os.getenv("AGENT_PORT", settings["agent"].get("mcp_port", "8000")))
 

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__ = "0.9.6"
+__version__ = "0.9.8"

{flowcept-0.9.6.dist-info → flowcept-0.9.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flowcept
-Version: 0.9.6
+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'
@@ -38,6 +39,7 @@ Requires-Dist: psutil>=6.1.1; extra == 'all'
 Requires-Dist: py-cpuinfo; extra == 'all'
 Requires-Dist: pyarrow; extra == 'all'
 Requires-Dist: pymongo; extra == 'all'
+Requires-Dist: pymupdf; extra == 'all'
 Requires-Dist: pytest; extra == 'all'
 Requires-Dist: pyyaml; extra == 'all'
 Requires-Dist: redis; extra == 'all'
@@ -87,13 +89,28 @@ 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'
+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'
+Requires-Dist: speechrecognition; extra == 'llm-agent-audio'
+Requires-Dist: streamlit; extra == 'llm-agent-audio'
+Requires-Dist: streamlit-mic-recorder; extra == 'llm-agent-audio'
 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'
 Provides-Extra: lmdb
 Requires-Dist: lmdb; extra == 'lmdb'

{flowcept-0.9.6.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=xw9cdk-bDkR4_bV2jBkDCe9__na9LKJW5tUG32by-m4,8216
-flowcept/version.py,sha256=52f8jJknjzSRjyruDcKgGzkV7OsLh2SvZl5sAIsExvU,306
+flowcept/configs.py,sha256=aXgBkBpTs4_4MpvAe76aQ5lXl1gTmgk92bFiNqMQXPM,8382
+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
@@ -9,18 +9,19 @@ flowcept/agents/dynamic_schema_tracker.py,sha256=TsmXRRkyUkqB-0bEgmeqSms8xj1tMMJ
 flowcept/agents/flowcept_agent.py,sha256=1sidjnNMdG0S6lUKBvml7ZfIb6o3u7zc6HNogsJbl9g,871
 flowcept/agents/flowcept_ctx_manager.py,sha256=-WmkddzzFY2dnU9LbZaoY4-5RcSAQH4FziEJgcC5LEI,7083
 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=61JpFKu-yd7luWVBW6HQYd3feOmupR01tYsZxl804No,9517
+flowcept/agents/gui/agent_gui.py,sha256=jsKPxJbXL2C2tXyNKpJnuVhSFktc0IpXyccW158rSWU,2752
+flowcept/agents/gui/audio_utils.py,sha256=piA_dc36io1sYqLF6QArS4AMl-cfDa001jGhYz5LkB4,4279
+flowcept/agents/gui/gui_utils.py,sha256=cQVhOgnfxJNUVZyXyO8f40nB1yaKAKVtBrwQmJjL0B0,14933
 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=OWVyToJL3w16zjycA0U0oRIx3XQRuklg0wqiUOny_1U,3892
-flowcept/agents/prompts/in_memory_query_prompts.py,sha256=70f4u3iFP9u1-CBM8yZR2cBu4qvxBe6FiKXLhRK8RCs,19634
+flowcept/agents/prompts/general_prompts.py,sha256=Mj6dMdrnJfq-bibi1XQVNZ8zx5MZUwxTvYY_qijPfoI,3894
+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=_c8NCMU32u2HOvEDMTSDptmHZYMMh48WRkZWBayZGaY,3206
+flowcept/agents/tools/general_tools.py,sha256=KS7ZTf1UbTxg0yQ6zCxh1g3NzcliYKWdurMArhPowxs,3248
 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=2kDmjz2cTN7q3eMjoTo4iruoyRTS0i370hSBYq2FZgA,25978
+flowcept/agents/tools/in_memory_queries/in_memory_queries_tools.py,sha256=GcfAiUBhQ1DU3QKk0kAy9TSq8XmZw691Xs0beZoO76A,25984
 flowcept/agents/tools/in_memory_queries/pandas_agent_utils.py,sha256=xyrZupR86qoUptnnQ7PeF0LTzSOquEK2cjc0ghT1KBs,9018
 flowcept/analytics/__init__.py,sha256=46q-7vsHq_ddPNrzNnDgEOiRgvlx-5Ggu2ocyROMV0w,641
 flowcept/analytics/analytics_utils.py,sha256=FRJdBtQa7Hrk2oR_FFhmhmMf3X6YyZ4nbH5RIYh7KL4,8753
@@ -31,7 +32,7 @@ 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=bJed8Jbo4Mxk6aRVt3sCn4_KxfV5jWXwAIQWwuqHm3U,13846
+flowcept/commons/task_data_preprocess.py,sha256=-ceLexv2ZfZOAYF43DPagGwQPgt_L_lNKuK8ZCpnzXs,13914
 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
@@ -45,7 +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
@@ -53,7 +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
@@ -93,9 +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=WSwpz8vmyx3oEsO6skV1KbFkYMDz-yIVQC6xlbUMDXs,6756
-flowcept-0.9.6.dist-info/METADATA,sha256=Bv9ZnCip57dtrn0Hv0GaT_i8CX3DfEGn6Ngclb7P-9Y,31581
-flowcept-0.9.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-flowcept-0.9.6.dist-info/entry_points.txt,sha256=i8q67WE0201rVxYI2lyBtS52shvgl93x2Szp4q8zMlw,47
-flowcept-0.9.6.dist-info/licenses/LICENSE,sha256=r5-2P6tFTuRGWT5TiX32s1y0tnp4cIqBEC1QjTaXe2k,1086
-flowcept-0.9.6.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: 0.9.6 # 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.
@@ -91,6 +91,7 @@ agent:
   model: '?'
   service_provider: '?'
   model_kwargs: {}
+  audio_enabled: false
 
 databases: