[Module] agent_deployer module by royischoss · Pull Request #937 · mlrun/functions

royischoss · 2025-12-07T09:23:44Z

Adding a Model deployer module to the function hub, allows the user to import a handler for the function ,graph creation and model monitoring configuration if desired

https://iguazio.atlassian.net/browse/FHUB-165

review-notebook-app · 2025-12-07T09:23:49Z

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

davesh0812

Nice.
Few comments :)

davesh0812 · 2025-12-07T09:42:00Z

+        if self.project:
+            self._project_name = self.project.metadata.name
+            return self._project_name
+        raise mlrun.errors.MLRunInvalidArgumentError("No current project found to get project name")


Suggested change

raise mlrun.errors.MLRunInvalidArgumentError("No current project found to get project name")

raise mlrun.errors.MLRunInvalidArgumentError("No active project detected, unable to resolve project name")

davesh0812 · 2025-12-07T09:47:36Z

+            tsdb_profile = DatastoreProfileTDEngine(
+                name="tdengine-tsdb-profile",
+                user="root",
+                password="taosdata",
+                host=f"tdengine-tsdb.{mlrun_namespace}.svc.cluster.local",
+                port="6041",
+            )


Please add a story under https://iguazio.atlassian.net/browse/ML-11482.
The story is אם replace TDEngine to TimeScale for the next version of this Module.
Also because of that. we should define that the latest MLrun to use this version is 1.10.*

davesh0812 · 2025-12-07T09:48:28Z

+            return self._project_name
+        raise mlrun.errors.MLRunInvalidArgumentError("No current project found to get project name")
+
+    def deploy_function(self, enable_tracking: bool = True):


Suggested change

def deploy_function(self, enable_tracking: bool = True):

def deploy_function(self, enable_tracking: bool = True) -> ServingRuntime:

And I think Saar want to have to methods:

get_function

deploy_function

davesh0812 · 2025-12-07T09:49:23Z

+            output_schema: Optional[list[str]] = None,
+            requirements: Optional[list[str]] = None,
+            image: Optional[str] = "mlrun/mlrun",
+            set_model_monitoring: Optional[bool] = False,


Suggested change

set_model_monitoring: Optional[bool] = False,

set_model_monitoring: bool = False,

OR

Suggested change

set_model_monitoring: Optional[bool] = False,

set_model_monitoring: Optional[bool] = None,

Same for the image param

davesh0812 · 2025-12-07T09:52:14Z

+        try:
+            self.project.enable_model_monitoring(
+                base_period=10,
+                image=self.image,


Here the image should be the default.. so you don't really need to pass an image

davesh0812 · 2025-12-07T09:55:15Z

+                deploy_histogram_data_drift_app=False
+            )
+        except (mlrun.errors.MLRunConflictError, mlrun.errors.MLRunHTTPError) as e:
+            print(e)


davesh0812 · 2025-12-07T09:55:38Z

+hidden: false
+labels:
+  author: Iguazio
+mlrunVersion: 1.10.0-rc41


Suggested change

mlrunVersion: 1.10.0-rc41

mlrunVersion: 1.10.0

davesh0812 · 2025-12-07T10:19:41Z

+    }
+   ],
+   "source": [
+    "func.invoke(\"./\", {\"question\" : \"If a pizza costs $18.75 and I want to buy 3, plus a 15% tip, what is the total cost?\"})"


lets put the invoke part before the MM app deployment

davesh0812 · 2025-12-07T10:21:27Z

+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "#### Write your monitoring application:",


Lets explain that this part is optional and not related to this module

* replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com>

* Cherry Pick from Development (#941) * replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * small fix notebook * remove changes in README.md * remove changes in README.md --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com>

* Cherry Pick from Development (#941) * replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Remove tensor flag, and fix notebool --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com>

* Cherry Pick from Development (mlrun#941) * replace author to Iguazio manually (mlrun#905) * Organize CLI directory + new CLI for generating item.yaml files (mlrun#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (mlrun#908) * avoid noise reduction unit test (mlrun#909) * Add histogram-data-drift monitoring application module (without example) (mlrun#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (mlrun#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (mlrun#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (mlrun#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (mlrun#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (mlrun#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (mlrun#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (mlrun#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (mlrun#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (mlrun#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (mlrun#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (mlrun#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (mlrun#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * small fix notebook * remove changes in README.md * remove changes in README.md --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com>

* Cherry Pick from Development (mlrun#941) * replace author to Iguazio manually (mlrun#905) * Organize CLI directory + new CLI for generating item.yaml files (mlrun#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (mlrun#908) * avoid noise reduction unit test (mlrun#909) * Add histogram-data-drift monitoring application module (without example) (mlrun#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (mlrun#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (mlrun#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (mlrun#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (mlrun#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (mlrun#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (mlrun#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (mlrun#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (mlrun#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (mlrun#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (mlrun#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (mlrun#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (mlrun#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Remove tensor flag, and fix notebool --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com>

* replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] * [Infra] Add 'Steps' to 'mlrun/hub-assets' and adjust CI/CD workflow to support it (#942) * first draft to support steps * correct branch name to test workflow * mlrun version * fix test * create a marketplace artifact * final workflow * add docstring to test the ui docs html * modify the readme to different colums set * no need for now * remove the dummy step files for now * chore(readme): auto-update asset tables [skip ci] * add default-handler to the step template (#947) * [AgentDeployer] Notebook prompt fix (#946) * Cherry Pick from Development (#941) * replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * small fix notebook * remove changes in README.md * remove changes in README.md --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> * [Module] Add vLLM module application (#943) * vLLM module first commit * Chane the module name * Fix generationDate format in item.yaml Correct the format of the generationDate field. * Fix test assertion for vllm_proxy_app type * Add copyright and module description to vllm_module.py Added copyright information and module description. * Update modules/src/vllm_module/vllm_module.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * Update modules/src/vllm_module/vllm-module.ipynb Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * Enhance description of vLLM module Updated the description to provide more details about the vLLM module's functionality and configuration options. * Add docstring for VLLMModule class Added docstring to VLLMModule class to describe its purpose and functionality. * Add validation for tensor_parallel_size against gpus * Update item.yaml --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * chore(readme): auto-update asset tables [skip ci] * fix nb name (#948) * [Module] vLLM module with notebook (#952) * Cherry Pick from Development (#941) * replace author to Iguazio manually (#905) * Organize CLI directory + new CLI for generating item.yaml files (#906) * create a CLI for generating item.yaml and organize the CLI directory * modify comments to module * PR fixes * Update cli/common/generate_item_yaml.py Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> --------- Co-authored-by: Eyal Danieli <eyal_danieli@mckinsey.com> * fill count events notebook (#908) * avoid noise reduction unit test (#909) * Add histogram-data-drift monitoring application module (without example) (#911) * histogram data drift module with empty example notebook * post review fixes * chore(readme): auto-update asset tables [skip ci] * Fill histogram-data-drift example notebook (#912) * fill data-drift nb * post review fixes * Add evidently demo app monitoring application module (without example) (#913) * sphinx build docs bug fix * add evidently demo app module (empty example notebook) * post review changes * chore(readme): auto-update asset tables [skip ci] * [Translate] Require torch>=2.6 for the translate function to work properly (#915) * lock torch valid version * edit the item.yaml and generated function.yaml * update mlrun version * [CLI] Generated READMEs are produced with broken links to the items (#918) * fix * test fix * test fix * test fix * test fix * final workflow * chore(readme): auto-update asset tables [skip ci] * OpenAI Module without notebook (#917) * First commit OpenAI Module * First commit OpenAI Module * Update example filename in item.yaml * Delete modules/src/openai_proxy/requirements.txt No need due to no unitest * Update item.yaml for OpenAI application configuration * Update modules/src/openai_proxy/openai.py Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * Change category name from 'GenAI' to 'genai' * Update package requirements with version constraints * Second commit adding notebook * Refactor OpenAI proxy to use base64 encoded script Refactor OpenAI proxy implementation to use base64 encoded script and update FastAPI app configuration. * Change deployment method to OpenAIModule * Third commit adding notebook * Third commit adding notebook * Remove package requirements from item.yaml Removed specific requirements for fastapi and requests. * Rename item and update kind in YAML * Update openai.py * Third commit adding notebook * Fix after review * Fix after review --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * [Evidently] Fill example notebook (#919) * add notebook + rename directory + correct evidently version * remove extra cell * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * [CLI + Modules] Fix time format in generate item yaml script (#922) * fix time format for evidently and hist * fix cli script * fix datetime format * chore(readme): auto-update asset tables [skip ci] * chore(readme): auto-update asset tables [skip ci] * Fix CMD first commit * Fix CMD second commit * remove max-width restriction from the main content (#929) * add test, requirement file and notebook * fix cli/utils/helpers.py * [Modules] Modify Evidently & Histogram monitoring apps example notebooks to the change in evaluate() (#934) * histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * fix to histogram_data_drift.ipynb * evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently_iris.ipynb * fix evidently dependency * add dependency * remove [ui] from evidently dependency * change notebook name to: openai_proxy_app * [Docs] Add guidelines for contributing new functions or modules (#931) * CONTRIBUTING.md * CONTRIBUTING.md * improvements * [Module] Updated the requirements for OpenAI module (#939) * Updated the requirements * Added Deafult model for credentials * Pin dependencies to specific versions in item.yaml * Update dependencies in openai_proxy_app.py * Specify versions for dependencies in requirements.txt * Fix environment variable access for OPENAI_DEFAULT_MODEL * change notebook name to: openai_proxy_app * [Module] agent_deployer module (#937) * first commit * added all modules * fixes from review and notebook adjustments * added unit tests and documentation * remove log * small fix * cr fixes * get_function fix * cr fixes working deployment * small fix notebook * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Chane the vllm-module.ipynb output error ,vllm_app. * Remove tensor flag, and fix notebool --------- Co-authored-by: Eyal Danieli <eyald@iguazio.com> Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com> * chore(readme): auto-update asset tables [skip ci] --------- Co-authored-by: Daniel Perez <100069700+danielperezz@users.noreply.github.com> Co-authored-by: iguazio-cicd <iguaziocicd@gmail.com> Co-authored-by: guylei-code <guyleibu@gmail.com> Co-authored-by: amitnGiniApps <amitn@gini-apps.com> Co-authored-by: Roy Schossberger <85231212+royischoss@users.noreply.github.com>

royischoss added 5 commits November 25, 2025 16:21

first commit

9b371a7

added all modules

1c3e448

fixes from review and notebook adjustments

808f1f0

added unit tests and documentation

a740fcd

remove log

58f8a41

small fix

1133ae9

davesh0812 reviewed Dec 7, 2025

View reviewed changes

royischoss added 4 commits December 8, 2025 10:16

cr fixes

cb71692

get_function fix

91f0661

cr fixes working deployment

5d19797

small fix notebook

bafd7ba

davesh0812 approved these changes Dec 10, 2025

View reviewed changes

Eyal-Danieli merged commit 1e19e97 into mlrun:development Dec 10, 2025
3 checks passed

Eyal-Danieli mentioned this pull request Dec 14, 2025

Cherry Pick from Development #941

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Module] agent_deployer module#937

[Module] agent_deployer module#937
Eyal-Danieli merged 10 commits into
mlrun:developmentfrom
royischoss:ml-11319

royischoss commented Dec 7, 2025 •

edited

Loading

Uh oh!

review-notebook-app Bot commented Dec 7, 2025

Uh oh!

davesh0812 left a comment

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025 •

edited

Loading

Uh oh!

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

davesh0812 Dec 7, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

	raise mlrun.errors.MLRunInvalidArgumentError("No current project found to get project name")
	raise mlrun.errors.MLRunInvalidArgumentError("No active project detected, unable to resolve project name")

	def deploy_function(self, enable_tracking: bool = True):
	def deploy_function(self, enable_tracking: bool = True) -> ServingRuntime:

	set_model_monitoring: Optional[bool] = False,
	set_model_monitoring: bool = False,

	set_model_monitoring: Optional[bool] = False,
	set_model_monitoring: Optional[bool] = None,

Conversation

royischoss commented Dec 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

review-notebook-app Bot commented Dec 7, 2025

Uh oh!

davesh0812 left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

davesh0812 Dec 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

royischoss commented Dec 7, 2025 •

edited

Loading

davesh0812 Dec 7, 2025 •

edited

Loading