flowcept 0.9.12__tar.gz → 0.9.16__tar.gz

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/checks.yml

@@ -14,7 +14,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-          cache: "pip"
+          # cache: "pip"
 
       - name: Install package and dependencies
         run: |

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-llm-tests.yml

@@ -23,7 +23,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Show OS Info
         run: '[[ "$OSTYPE" == "linux-gnu"* ]] && { echo "OS Type: Linux"; (command -v lsb_release &> /dev/null && lsb_release -a) || cat /etc/os-release; uname -r; } || [[ "$OSTYPE" == "darwin"* ]] && { echo "OS Type: macOS"; sw_vers; uname -r; } || echo "Unsupported OS type: $OSTYPE"'

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-tests-all-dbs.yml

@@ -24,7 +24,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Show OS Info
         run: '[[ "$OSTYPE" == "linux-gnu"* ]] && { echo "OS Type: Linux"; (command -v lsb_release &> /dev/null && lsb_release -a) || cat /etc/os-release; uname -r; } || [[ "$OSTYPE" == "darwin"* ]] && { echo "OS Type: macOS"; sw_vers; uname -r; } || echo "Unsupported OS type: $OSTYPE"'

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-tests-kafka.yml

@@ -28,7 +28,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Run docker compose
         run: docker compose -f deployment/compose-kafka.yml up -d

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-tests-py313.yml

@@ -23,7 +23,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Show OS Info
         run: '[[ "$OSTYPE" == "linux-gnu"* ]] && { echo "OS Type: Linux"; (command -v lsb_release &> /dev/null && lsb_release -a) || cat /etc/os-release; uname -r; } || [[ "$OSTYPE" == "darwin"* ]] && { echo "OS Type: macOS"; sw_vers; uname -r; } || echo "Unsupported OS type: $OSTYPE"'

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-tests-simple.yml

@@ -26,7 +26,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Show OS Info
         run: '[[ "$OSTYPE" == "linux-gnu"* ]] && { echo "OS Type: Linux"; (command -v lsb_release &> /dev/null && lsb_release -a) || cat /etc/os-release; uname -r; } || [[ "$OSTYPE" == "darwin"* ]] && { echo "OS Type: macOS"; sw_vers; uname -r; } || echo "Unsupported OS type: $OSTYPE"'

{flowcept-0.9.12 → flowcept-0.9.16}/.github/workflows/run-tests.yml

@@ -26,7 +26,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: "pip"
+          # cache: "pip"
 
       - name: Show OS Info
         run: 'case "${OSTYPE:-}" in linux*) echo "OS Type: Linux"; (command -v lsb_release >/dev/null 2>&1 && lsb_release -a || cat /etc/os-release); uname -r ;; darwin*) echo "OS Type: macOS"; sw_vers || true; uname -r ;; *) echo "Unsupported OS type: ${OSTYPE:-unknown}" ;; esac'

{flowcept-0.9.12 → flowcept-0.9.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flowcept
-Version: 0.9.12
+Version: 0.9.16
 Summary: Capture and query workflow provenance data using data observability
 Author: Oak Ridge National Laboratory
 License-Expression: MIT

{flowcept-0.9.12 → flowcept-0.9.16}/docs/publications/README.md

@@ -15,8 +15,7 @@ PDF: https://arxiv.org/pdf/2308.09004.pdf
 
 **PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows**  
 R. Souza, A. Gueroudji, S. DeWitt, D. Rosendo, T. Ghosal, R. Ross, P. Balaprakash, and R. Ferreira da Silva,  
-*IEEE International Conference on e-Science*, Chicago, USA., 2025.  
-Publisher: IEEE.  
+*IEEE International Conference on e-Science*, Chicago, USA., 2025.
 PDF: https://arxiv.org/pdf/2508.02866  
 
 ---
@@ -34,7 +33,26 @@ R. Souza, T. Poteet, B. Etz, D. Rosendo, A. Gueroudji, W. Shin, P. Balaprakash,
 *Workflows in Support of Large-Scale Science (WORKS) co-located with the ACM/IEEE International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)*, St. Louis, USA, 2025.  
 doi: [10.1145/3731599.3767582](https://doi.org/10.1145/3731599.3767582)  
 
-### Bixtex
+
+### Papers that used Flowcept
+
+
+**Toward a Persistent Event-Streaming System for High-Performance Computing Applications**
+M. Dorier, A. Gueroudji, V. Hayot-Sasson, H. Nguyen, S. Ockerman, R. Souza, T. Bicer, H. Pan, P. Carns, K. Chard, and others
+*Frontiers in High Performance Computing*, 2025.
+doi: [10.3389/fhpcp.2025.1638203](https://doi.org/10.3389/fhpcp.2025.1638203)
+PDF: https://web.cels.anl.gov/~woz/papers/Mofka_2025.pdf
+
+---
+
+**AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities**
+D. Rosendo, S. DeWitt, R. Souza, P. Austria, T. Ghosal, M. McDonnell, R. Miller, T. Skluzacek, J. Haley, B. Turcksin, and others
+*Extreme-Scale Experiment-in-the-Loop Computing (XLOOP) co-located with the ACM/IEEE International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)*, 2025.
+PDF: https://rafaelsilva.com/files/publications/rosendo2025xloop.pdf
+
+--- 
+
+### Bibtex
 
 ```
 @inproceedings{souza2023towards,
@@ -47,7 +65,6 @@ doi: [10.1145/3731599.3767582](https://doi.org/10.1145/3731599.3767582)
   year={2023},
   abstract={Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.}
 }
-
 ```
 
 ```latex
@@ -89,3 +106,29 @@ doi: [10.1145/3731599.3767582](https://doi.org/10.1145/3731599.3767582)
   keywords  = {scientific workflows, provenance, LLM agents, Large language models, AI agents, agentic workflows, agentic provenance}
 }
 ```
+
+```latex
+@article{dorier2025toward,
+  author = {Dorier, Matthieu and Gueroudji, Amal and Hayot-Sasson, Valerie and Nguyen, Hai and Ockerman, Seth and Souza, Renan and Bicer, Tekin and Pan, Haochen and Carns, Philip and Chard, Kyle and others},
+  doi = {10.3389/fhpcp.2025.1638203},
+  journal = {Frontiers in High Performance Computing},
+  keyword = {HPC, I/O, Streaming, Mochi, Mofka, Kafka, Redpanda},
+  link = {https://www.frontiersin.org/journals/high-performance-computing/articles/10.3389/fhpcp.2025.1638203/abstract},
+  publisher = {Frontiers in High Performance Computing},
+  title = {Toward a Persistent Event-Streaming System for High-Performance Computing Applications},
+  volume = {3},
+  year = {2025}
+}
+```
+
+```latex
+@inproceedings{rosendo2025ai,
+  address = {St Louis, MO, USA},
+  author = {Rosendo, Daniel and DeWitt, Stephen and Souza, Renan and Austria, Phillipe and Ghosal, Tirthankar and McDonnell, Marshall and Miller, Ross and Skluzacek, Tyler J and Haley, James and Turcksin, Bruno and others},
+  booktitle = {Extreme-Scale Experiment-in-the-Loop Computing ({XLOOP}) co-located with the {ACM}/{IEEE} International Conference for High Performance Computing, Networking, Storage, and Analysis ({SC})},
+  pdf = {https://rafaelsilva.com/files/publications/rosendo2025xloop.pdf},
+  publisher = {ACM},
+  title = {AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities},
+  year = {2025}
+}
+```

flowcept-0.9.16/resources/ontology/catalog-v001.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<catalog prefer="public" xmlns="urn:oasis:names:tc:entity:xmlns:xml:catalog">
+    <group id="Folder Repository, directory=, recursive=true, Auto-Update=true, version=2" prefer="public" xml:base=""/>
+</catalog>

flowcept-0.9.16/resources/ontology/prov_agent.owl

@@ -0,0 +1,102 @@
+@prefix prov_ag   <http://example.org/aiprov#> .
+@prefix prov: <http://www.w3.org/ns/prov#> .
+@prefix rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix owl:  <http://www.w3.org/2002/07/owl#> .
+@prefix xsd:  <http://www.w3.org/2001/XMLSchema#> .
+
+prov_ag a owl:Ontology ;
+  rdfs:label "AI Agent Provenance Ontology (PROV-AGENT)" ;
+  rdfs:comment "Extends PROV-O to model agentic workflows, LLM calls, tools, and data per the given graph." ;
+  owl:imports <http://www.w3.org/ns/prov-o#> .
+
+### Core classes
+prov_agDataObject a owl:Class ;
+  rdfs:subClassOf prov:Entity ;
+  rdfs:label "DataObject" .
+
+prov_agDomainData a owl:Class ;
+  rdfs:subClassOf prov_agDataObject ,
+    [ a owl:Restriction ; owl:onProperty prov:wasGeneratedBy ; owl:someValuesFrom prov_agTask ] ;
+  rdfs:label "DomainData" .
+
+prov_agTelemetryData a owl:Class ;
+  rdfs:subClassOf prov_agDataObject ,
+    [ a owl:Restriction ; owl:onProperty prov:wasGeneratedBy ; owl:someValuesFrom prov_agTask ] ;
+  rdfs:label "TelemetryData" .
+
+prov_agSchedulingData a owl:Class ;
+  rdfs:subClassOf prov_agDataObject ,
+    [ a owl:Restriction ; owl:onProperty prov:wasGeneratedBy ; owl:someValuesFrom prov_agTask ] ;
+  rdfs:label "SchedulingData" .
+
+prov_agPrompt a owl:Class ;
+  rdfs:subClassOf prov_agDataObject ;
+  rdfs:label "Prompt" .
+
+prov_agResponseData a owl:Class ;
+  rdfs:subClassOf prov_agDataObject ,
+    [ a owl:Restriction ; owl:onProperty prov:wasGeneratedBy ; owl:someValuesFrom prov_agAIModelInvocation ] ;
+  rdfs:label "ResponseData" .
+
+prov_agModel a owl:Class ;
+  rdfs:subClassOf prov:Entity ;
+  rdfs:label "AI Model" .
+
+### Activities
+prov_agCampaign a owl:Class ;
+  rdfs:subClassOf prov:Activity ,
+    [ a owl:Restriction ; owl:onProperty prov_aghasMemberActivity ; owl:someValuesFrom prov_agWorkflow ] ;
+  rdfs:label "Campaign" .
+
+prov_agWorkflow a owl:Class ;
+  rdfs:subClassOf prov:Activity ,
+    [ a owl:Restriction ; owl:onProperty prov_aghasMemberActivity ; owl:someValuesFrom prov_agTask ] ,
+    [ a owl:Restriction ; owl:onProperty prov_aghasMemberActivity ; owl:someValuesFrom prov_agAgentTool ] ;
+  rdfs:label "Workflow" .
+
+prov_agTask a owl:Class ;
+  rdfs:subClassOf prov:Activity ,
+    [ a owl:Restriction ; owl:onProperty prov:used ; owl:someValuesFrom prov_agDomainData ] ,
+    [ a owl:Restriction ; owl:onProperty prov:generated ; owl:someValuesFrom prov_agDomainData ] ,
+    [ a owl:Restriction ; owl:onProperty prov:generated ; owl:someValuesFrom prov_agTelemetryData ] ,
+    [ a owl:Restriction ; owl:onProperty prov:generated ; owl:someValuesFrom prov_agSchedulingData ] ;
+  rdfs:label "Task" .
+
+prov_agAgentTool a owl:Class ;
+  rdfs:subClassOf prov:Activity ,
+    [ a owl:Restriction ; owl:onProperty prov:used ; owl:someValuesFrom prov_agDataObject ] ,
+    [ a owl:Restriction ; owl:onProperty prov:wasAssociatedWith ; owl:someValuesFrom prov_agAIAgent ] ,
+    [ a owl:Restriction ; owl:onProperty prov:wasInformedBy ; owl:someValuesFrom prov_agAIModelInvocation ] ;
+  rdfs:label "AgentTool" .
+
+prov_agAIModelInvocation a owl:Class ;
+  rdfs:subClassOf prov:Activity ,
+    [ a owl:Restriction ; owl:onProperty prov:used ; owl:someValuesFrom prov_agPrompt ] ,
+    [ a owl:Restriction ; owl:onProperty prov:used ; owl:someValuesFrom prov_agModel ] ;
+  rdfs:label "AI Model Invocation" .
+
+### Agent
+prov_agAIAgent a owl:Class ;
+  rdfs:subClassOf prov:SoftwareAgent ;
+  rdfs:label "AIAgent" .
+
+### Custom property to mirror diagram’s hadMember (Activity-to-Activity)
+prov_aghasMemberActivity a owl:ObjectProperty ;
+  rdfs:label "hadMember" ;
+  rdfs:comment "Structural membership of sub-activities within an activity, e.g., a workflow containing tasks or tools." ;
+  rdfs:domain prov:Activity ;
+  rdfs:range  prov:Activity ;
+  rdfs:subPropertyOf rdfs:member .
+
+### Useful PROV-aware inferences
+# If an entity wasGeneratedBy an activity that wasAssociatedWith an agent,
+# then attribute the entity to that agent.
+prov:wasAttributedTo owl:propertyChainAxiom ( prov:wasGeneratedBy prov:wasAssociatedWith ) .
+
+### Optional naming for convenience individuals (URIs to mint in data)
+# Classes above define the schema. Instances can use PROV-O relations directly, e.g.:
+# :t1 a prov_agTask ; prov:used :d_in .
+# :d_out a prov_agDomainData ; prov:wasGeneratedBy :t1 .
+# :tool1 a prov_agAgentTool ; prov:wasAssociatedWith :agent1 ; prov:wasInformedBy :llmCall1 .
+# :llmCall1 a prov_agAIModelInvocation ; prov:used :prompt1, :modelX .

{flowcept-0.9.12 → flowcept-0.9.16}/resources/sample_settings.yaml

@@ -1,4 +1,4 @@
-flowcept_version: 0.9.12 # Version of the Flowcept package. This setting file is compatible with this version.
+flowcept_version: 0.9.16 # 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.

{flowcept-0.9.12 → flowcept-0.9.16}/src/flowcept/agents/agents_utils.py

@@ -166,6 +166,21 @@ def build_llm_model(
             from flowcept.agents.llms.gemini25 import Gemini25LLM
 
             llm = Gemini25LLM(**_model_kwargs)
+    elif _service_provider == "openai":
+        from langchain_openai import ChatOpenAI
+
+        api_key = os.environ.get("OPENAI_API_KEY", AGENT.get("api_key"))
+        base_url = os.environ.get("OPENAI_BASE_URL", AGENT.get("llm_server_url") or None)  # optional
+        org = os.environ.get("OPENAI_ORG_ID", AGENT.get("organization", None))  # optional
+
+        init_kwargs = {"api_key": api_key}
+        if base_url:
+            init_kwargs["base_url"] = base_url
+        if org:
+            init_kwargs["organization"] = org
+
+        # IMPORTANT: use the merged kwargs so `model` and temps flow through
+        llm = ChatOpenAI(**init_kwargs, **_model_kwargs)
 
     else:
         raise Exception("Currently supported providers are sambanova, openai, azure, and google.")

{flowcept-0.9.12 → flowcept-0.9.16}/src/flowcept/cli.py

@@ -66,7 +66,7 @@ def init_settings(full: bool = False):
     settings_path_env = os.getenv("FLOWCEPT_SETTINGS_PATH", None)
     if settings_path_env is not None:
         print(f"FLOWCEPT_SETTINGS_PATH environment variable is set to {settings_path_env}.")
-        dest_path = settings_path_env
+        dest_path = Path(settings_path_env)
     else:
         dest_path = Path(os.path.join(configs._SETTINGS_DIR, "settings.yaml"))
 

{flowcept-0.9.12 → flowcept-0.9.16}/src/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__ = "0.9.12"
+__version__ = "0.9.16"