| Name | monocle-apptrace JSON |
| Version |
0.4.2
JSON |
| download |
| home_page | None |
| Summary | package with monocle genAI tracing |
| upload_time | 2025-06-26 15:21:25 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Monocle for tracing GenAI app code
**Monocle** helps developers and platform engineers building or managing GenAI apps monitor these in prod by making it easy to instrument their code to capture traces that are compliant with open-source cloud-native observability ecosystem.
**Monocle** is a community-driven OSS framework for tracing GenAI app code governed as a [Linux Foundation AI & Data project](https://lfaidata.foundation/projects/monocle/).
## Why Monocle
Monocle is built for:
- **app developers** to trace their app code in any environment without lots of custom code decoration
- **platform engineers** to instrument apps in prod through wrapping instead of asking app devs to recode
- **GenAI component providers** to add observability features to their products
- **enterprises** to consume traces from GenAI apps in their existing open-source observability stack
Benefits:
- Monocle provides an implementation + package, not just a spec
- No expertise in OpenTelemetry spec required
- No bespoke implementation of that spec required
- No last-mile GenAI domain specific code required to instrument your app
- Monocle provides consistency
- Connect traces across app code executions, model inference or data retrievals
- No cleansing of telemetry data across GenAI component providers required
- Works the same in personal lab dev or org cloud prod environments
- Send traces to location that fits your scale, budget and observability stack
- Monocle is fully open source and community driven
- No vendor lock-in
- Implementation is transparent
- You can freely use or customize it to fit your needs
## What Monocle provides
- Easy to [use](#use-monocle) code instrumentation
- OpenTelemetry compatible format for [spans](src/monocle_apptrace/metamodel/spans/span_format.json).
- Community-curated and extensible [metamodel](src/monocle_apptrace/metamodel/README.md) for consisent tracing of GenAI components.
- Export to local and cloud storage
## Use Monocle
- Get the Monocle package
```
pip install monocle_apptrace
```
- Instrument your app code
- Import the Monocle package
```
from monocle_apptrace.instrumentor import setup_monocle_telemetry
```
- Setup instrumentation in your ```main()``` function
```
setup_monocle_telemetry(workflow_name="your-app-name")
```
- (Optionally) Modify config to alter where traces are sent
See [Monocle user guide](Monocle_User_Guide.md) for more details.
## Roadmap
Goal of Monocle is to support tracing for apps written in *any language* with *any LLM orchestration or agentic framework* and built using models, vectors, agents or other components served up by *any cloud or model inference provider*.
Current version supports:
- Language: (🟢) Python , (🔜) [Typescript](https://github.com/monocle2ai/monocle-typescript)
- LLM-frameworks: (🟢) Langchain, (🟢) Llamaindex, (🟢) Haystack, (🔜) Flask
- LLM inference providers: (🟢) OpenAI, (🟢) Azure OpenAI, (🟢) Nvidia Triton, (🔜) AWS Bedrock, (🔜) Google Vertex, (🔜) Azure ML, (🔜) Hugging Face
- Vector stores: (🟢) FAISS, (🔜) OpenSearch, (🔜) Milvus
- Exporter: (🟢) stdout, (🟢) file, (🔜) Azure Blob Storage, (🔜) AWS S3, (🔜) Google Cloud Storage
## Get involved
### Provide feedback
- Submit issues and enhancements requests via Github issues
### Contribute
- Monocle is community based open source project. We welcome your contributions. Please refer to the CONTRIBUTING and CODE_OF_CONDUCT for guidelines. The [contributor's guide](CONTRIBUTING.md) provides technical details of the project.
Raw data
{
"_id": null,
"home_page": null,
"name": "monocle-apptrace",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/ec/c5/b5b20cd6f6f9b8cc4fac81475e734d349db024ca88d3e124cea6b1f3b9c0/monocle_apptrace-0.4.2.tar.gz",
"platform": null,
"description": "# Monocle for tracing GenAI app code\n\n**Monocle** helps developers and platform engineers building or managing GenAI apps monitor these in prod by making it easy to instrument their code to capture traces that are compliant with open-source cloud-native observability ecosystem. \n\n**Monocle** is a community-driven OSS framework for tracing GenAI app code governed as a [Linux Foundation AI & Data project](https://lfaidata.foundation/projects/monocle/). \n\n## Why Monocle\n\nMonocle is built for: \n- **app developers** to trace their app code in any environment without lots of custom code decoration \n- **platform engineers** to instrument apps in prod through wrapping instead of asking app devs to recode\n- **GenAI component providers** to add observability features to their products \n- **enterprises** to consume traces from GenAI apps in their existing open-source observability stack\n\nBenefits:\n- Monocle provides an implementation + package, not just a spec \n - No expertise in OpenTelemetry spec required\n - No bespoke implementation of that spec required\n - No last-mile GenAI domain specific code required to instrument your app\n- Monocle provides consistency \n - Connect traces across app code executions, model inference or data retrievals\n - No cleansing of telemetry data across GenAI component providers required\n - Works the same in personal lab dev or org cloud prod environments\n - Send traces to location that fits your scale, budget and observability stack\n- Monocle is fully open source and community driven\n - No vendor lock-in\n - Implementation is transparent\n - You can freely use or customize it to fit your needs \n\n## What Monocle provides\n\n- Easy to [use](#use-monocle) code instrumentation\n- OpenTelemetry compatible format for [spans](src/monocle_apptrace/metamodel/spans/span_format.json). \n- Community-curated and extensible [metamodel](src/monocle_apptrace/metamodel/README.md) for consisent tracing of GenAI components. \n- Export to local and cloud storage \n\n## Use Monocle\n\n- Get the Monocle package\n \n```\n pip install monocle_apptrace \n```\n- Instrument your app code\n - Import the Monocle package\n ```\n from monocle_apptrace.instrumentor import setup_monocle_telemetry\n ```\n - Setup instrumentation in your ```main()``` function \n ``` \n setup_monocle_telemetry(workflow_name=\"your-app-name\")\n ``` \n- (Optionally) Modify config to alter where traces are sent\n\nSee [Monocle user guide](Monocle_User_Guide.md) for more details.\n \n\n## Roadmap \n\nGoal of Monocle is to support tracing for apps written in *any language* with *any LLM orchestration or agentic framework* and built using models, vectors, agents or other components served up by *any cloud or model inference provider*. \n\nCurrent version supports: \n- Language: (\ud83d\udfe2) Python , (\ud83d\udd1c) [Typescript](https://github.com/monocle2ai/monocle-typescript) \n- LLM-frameworks: (\ud83d\udfe2) Langchain, (\ud83d\udfe2) Llamaindex, (\ud83d\udfe2) Haystack, (\ud83d\udd1c) Flask\n- LLM inference providers: (\ud83d\udfe2) OpenAI, (\ud83d\udfe2) Azure OpenAI, (\ud83d\udfe2) Nvidia Triton, (\ud83d\udd1c) AWS Bedrock, (\ud83d\udd1c) Google Vertex, (\ud83d\udd1c) Azure ML, (\ud83d\udd1c) Hugging Face\n- Vector stores: (\ud83d\udfe2) FAISS, (\ud83d\udd1c) OpenSearch, (\ud83d\udd1c) Milvus\n- Exporter: (\ud83d\udfe2) stdout, (\ud83d\udfe2) file, (\ud83d\udd1c) Azure Blob Storage, (\ud83d\udd1c) AWS S3, (\ud83d\udd1c) Google Cloud Storage\n\n\n## Get involved\n### Provide feedback\n- Submit issues and enhancements requests via Github issues\n\n### Contribute\n- Monocle is community based open source project. We welcome your contributions. Please refer to the CONTRIBUTING and CODE_OF_CONDUCT for guidelines. The [contributor's guide](CONTRIBUTING.md) provides technical details of the project.\n\n",
"bugtrack_url": null,
"license": null,
"summary": "package with monocle genAI tracing",
"version": "0.4.2",
"project_urls": {
"Homepage": "https://github.com/monocle2ai/monocle",
"Issues": "https://github.com/monocle2ai/monocle/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "348a5614f683f8a061e884817da4d3d80b9db7016e7fea7d8b4303a6f2b7b44e",
"md5": "5f180cc2047cae1b35dbd0f81635093a",
"sha256": "98c45c23ce70fda6f6474f7ea733d34150ed4e3a90e8d9213bdf69fcdc07f105"
},
"downloads": -1,
"filename": "monocle_apptrace-0.4.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5f180cc2047cae1b35dbd0f81635093a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 103972,
"upload_time": "2025-06-26T15:21:24",
"upload_time_iso_8601": "2025-06-26T15:21:24.265385Z",
"url": "https://files.pythonhosted.org/packages/34/8a/5614f683f8a061e884817da4d3d80b9db7016e7fea7d8b4303a6f2b7b44e/monocle_apptrace-0.4.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ecc5b5b20cd6f6f9b8cc4fac81475e734d349db024ca88d3e124cea6b1f3b9c0",
"md5": "0f68899c670e4a4a95d1a79898aca78e",
"sha256": "42016f7f0397c47a48a0a4a75442b681089021e99681eb36c3b4099a0cd278ed"
},
"downloads": -1,
"filename": "monocle_apptrace-0.4.2.tar.gz",
"has_sig": false,
"md5_digest": "0f68899c670e4a4a95d1a79898aca78e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 63762,
"upload_time": "2025-06-26T15:21:25",
"upload_time_iso_8601": "2025-06-26T15:21:25.500530Z",
"url": "https://files.pythonhosted.org/packages/ec/c5/b5b20cd6f6f9b8cc4fac81475e734d349db024ca88d3e124cea6b1f3b9c0/monocle_apptrace-0.4.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-06-26 15:21:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "monocle2ai",
"github_project": "monocle",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"tox": true,
"lcname": "monocle-apptrace"
}
