[PR #90] [MERGED] feat: DataDog LLM Observability Pipeline #300

Closed
opened 2026-02-15 20:15:00 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/pipelines/pull/90
Author: @westbrook-ai
Created: 6/13/2024
Status: Merged
Merged: 6/17/2024
Merged by: @tjbck

Base: mainHead: feat-datadog-llmobs-filter


📝 Commits (4)

  • 30fa228 Working DataDog pipeline
  • cdb2367 Add Rust to Docker image, update requirements.txt
  • b983e8f Testing updated Dockerfile
  • 6d508be Resolved outlet issue

📊 Changes

6 files changed (+139 additions, -8 deletions)

View changed files

📝 .dockerignore (+2 -1)
📝 .gitignore (+2 -1)
📝 Dockerfile (+3 -5)
dev-docker.sh (+9 -0)
examples/filters/datadog_filter_pipeline.py (+121 -0)
📝 requirements.txt (+2 -1)

📄 Description

Adds a DataDog pipeline, a new Dockerfile image with Rust installed (which is required for the DataDog library to build and install correctly), and a new script to start a basic dev environment in Docker that includes Open WebUI, Ollama and Pipelines.

Here's an example of what you see in DataDog when you enable this pipeline and communicate with your LLMs through Open WebUI:
image

To correctly set Pipelines up for use with DataDog, you have to first build the Dockerfile.rust image, then spin up your Pipelines container using that image. A basic rundown of the steps is below:

  1. Sign up for a DataDog account.
  2. Create a .env file, and fill out the following variables:
DD_API_KEY=<your API key>
DD_LLMOBS_ENABLED=1
DD_LLMOBS_ML_APP=<your app name for the DataDog UI, such as "pipelines-test">
DD_LLMOBS_AGENTLESS_ENABLED=1
DD_SITE=<your DataDog site based on your selected region, such as us1.datadoghq.com>
  1. Start your environment locally using the commands below:
docker build -t datadog-pipelines -f Dockerfile.rust .
docker run -d -p 9099:9099 --add-host=host.docker.internal:host-gateway -v pipelines:/app/pipelines --name pipelines --restart always --env-file .env datadog-pipelines
# If you also want to start Open WebUI with integrated Ollama, run the command below
docker run -d -p 3000:8080 -v ~/.ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always -e OPENAI_API_BASE_URL=http://host.docker.internal:9099 -e OPENAI_API_KEY=0p3n-w3bu! ghcr.io/open-webui/open-webui:ollama
  1. Start a chat in Open WebUI, and validate that you see results in your DataDog LLM Observability UI

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/pipelines/pull/90 **Author:** [@westbrook-ai](https://github.com/westbrook-ai) **Created:** 6/13/2024 **Status:** ✅ Merged **Merged:** 6/17/2024 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `main` ← **Head:** `feat-datadog-llmobs-filter` --- ### 📝 Commits (4) - [`30fa228`](https://github.com/open-webui/pipelines/commit/30fa228a8400eb8a5684ee5e4be43938e731739c) Working DataDog pipeline - [`cdb2367`](https://github.com/open-webui/pipelines/commit/cdb2367493b68dc760e3b5ccba430ae02f1e123a) Add Rust to Docker image, update requirements.txt - [`b983e8f`](https://github.com/open-webui/pipelines/commit/b983e8f2578cc6335e675ed98b710de4efab9d11) Testing updated Dockerfile - [`6d508be`](https://github.com/open-webui/pipelines/commit/6d508be4961054c30f25b3eac4c07a83091e31ba) Resolved outlet issue ### 📊 Changes **6 files changed** (+139 additions, -8 deletions) <details> <summary>View changed files</summary> 📝 `.dockerignore` (+2 -1) 📝 `.gitignore` (+2 -1) 📝 `Dockerfile` (+3 -5) ➕ `dev-docker.sh` (+9 -0) ➕ `examples/filters/datadog_filter_pipeline.py` (+121 -0) 📝 `requirements.txt` (+2 -1) </details> ### 📄 Description Adds a DataDog pipeline, a new Dockerfile image with Rust installed (which is required for the DataDog library to build and install correctly), and a new script to start a basic dev environment in Docker that includes Open WebUI, Ollama and Pipelines. Here's an example of what you see in DataDog when you enable this pipeline and communicate with your LLMs through Open WebUI: <img width="1000" alt="image" src="https://github.com/open-webui/pipelines/assets/104535511/0813acf0-a9f9-4b45-a13a-22e8c653ddd9"> To correctly set Pipelines up for use with DataDog, you have to first build the `Dockerfile.rust` image, then spin up your Pipelines container using that image. A basic rundown of the steps is below: 1. Sign up for a DataDog account. 2. Create a `.env` file, and fill out the following variables: ``` DD_API_KEY=<your API key> DD_LLMOBS_ENABLED=1 DD_LLMOBS_ML_APP=<your app name for the DataDog UI, such as "pipelines-test"> DD_LLMOBS_AGENTLESS_ENABLED=1 DD_SITE=<your DataDog site based on your selected region, such as us1.datadoghq.com> ``` 3. Start your environment locally using the commands below: ``` docker build -t datadog-pipelines -f Dockerfile.rust . docker run -d -p 9099:9099 --add-host=host.docker.internal:host-gateway -v pipelines:/app/pipelines --name pipelines --restart always --env-file .env datadog-pipelines # If you also want to start Open WebUI with integrated Ollama, run the command below docker run -d -p 3000:8080 -v ~/.ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always -e OPENAI_API_BASE_URL=http://host.docker.internal:9099 -e OPENAI_API_KEY=0p3n-w3bu! ghcr.io/open-webui/open-webui:ollama ``` 4. Start a chat in Open WebUI, and validate that you see results in your DataDog LLM Observability UI --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-15 20:15:00 -05:00
yindo closed this issue 2026-02-15 20:15:00 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: open-webui/pipelines#300