Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dynatrace/obslab-llm-observability
Search for a holiday and get destination advice from an LLM. Observability by Dynatrace.
https://github.com/dynatrace/obslab-llm-observability
ai-observability application-observability demo dynatrace genai llm ollama openai pinecone rag-pipeline
Last synced: 3 days ago
JSON representation
Search for a holiday and get destination advice from an LLM. Observability by Dynatrace.
- Host: GitHub
- URL: https://github.com/dynatrace/obslab-llm-observability
- Owner: Dynatrace
- License: apache-2.0
- Created: 2024-05-22T01:28:13.000Z (8 months ago)
- Default Branch: ollama-pinecone
- Last Pushed: 2025-01-27T10:59:35.000Z (3 days ago)
- Last Synced: 2025-01-27T11:49:26.581Z (3 days ago)
- Topics: ai-observability, application-observability, demo, dynatrace, genai, llm, ollama, openai, pinecone, rag-pipeline
- Language: HTML
- Homepage: https://dynatrace.github.io/obslab-llm-observability/
- Size: 8.1 MB
- Stars: 5
- Watchers: 1
- Forks: 138
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# EasyTravel GPT Travel Advisor
Demo application for giving travel advice written in Python. Observability signals by [OpenTelemetry](https://opentelemetry.io).
Uses [Ollama](https://ollama.com/) and [PineCone](https://www.pinecone.io/) to generate advice for a given destination.
> **Note**
> This product is not officially supported by Dynatrace!
### Try it yourself
* Explore our sample dashboards on the [Dynatrace Playground](https://dynatr.ac/4dnkuLX).
* Implement AI observability in your environments with our detailed [Dynatrace Documentation](https://dynatr.ac/3XKxKEC).
[](http://www.youtube.com/watch?v=eW2KuWFeZyY)
## Configure Pinecone
Head over to https://app.pinecone.io/ and login into your account.
1. Create a new index called `travel-advisor` with the dimensions of **3200** and a `cosine` metric.
The index will store our knowledge source, which the RAG pipeline will use to augment the LLM's output of the travel recommendation.
The parameter 3200 is because for this demo, we are using the embedding model `orca-mini:3b` which returns vector of 3200 elements.
2. After creating and running the index, we can create an API key to connect.
Follow the [Pinecone documentation on authentication](https://dt-url.net/ji63ugh) to get the API key to connect to your Pinecone index and store it as Kubernetes secrets with the following command:
## Try it out yourself
[](https://codespaces.new/dynatrace-perfclinics/obslab-llm-observability?ref=ollama-pinecone)
## Developer Information Below
### Run Locally
Start [Ollama](https://github.com/ollama/ollama) locally by running `ollama serve`.
For this example, we'll use a simple model, `orca-mini:3b`.
You can pull it running `ollama run orca-mini:3b`.
Afterwards, you can start the application locally by running the following command.
```bash
export PINECONE_API_KEY=
export OTEL_ENDPOINT=https://.live.dynatrace.com/api/v2/otlp
export API_TOKEN=
python app.py
```
--------------------------
### Deploy on a Local K8S Cluster
You will need [Docker](https://docs.docker.com/engine/install/) or [Podman](https://podman.io/docs/installation) installed.
Create a cluster if you do not already have one:
```bash
kind create cluster --config .devcontainer/kind-cluster.yml --wait 300s
```
Customise and set some environment variables
```bash
export PINECONE_API_KEY=
export DT_ENDPOINT=https://.live.dynatrace.com
export DT_TOKEN=
```
Run the deployment script:
```bash
.devcontainer/deployment.sh
```