feat: update observability instructions

Signed-off-by: Tomas Dvorak <[email protected]>

README.md

@@ -15,14 +15,20 @@
 >
 > - [Docker](https://www.docker.com/)
 > - [Rancher](https://www.rancher.com/) - macOS users may want to use VZ instead of QEMU
+> - [Podman](https://podman.io/) - requires [compose](https://podman-desktop.io/docs/compose/setting-up-compose) and **rootful machine** (if your current machine is rootless, please create a new one)
 
 Get full visibility of the agent's inner working via our observability stack.
 
 - The [MLFlow](https://mlflow.org/) is used as UI for observability.
 - The [Bee Observe](https://github.com/i-am-bee/bee-observe) is the main Open-source observability service for Bee Agent Framework.
 - The [Bee Observe Connector](https://github.com/i-am-bee/bee-observe-connector) is the observability connector for Bee Agent Framework
 
+Configuration (ENV variables) can be found [here](./infra/observe/.env.docker).
+
 ### Steps
 
 1. Start all services related to Observe `npm run infra:start-observe`
-2. Start the agent using the observe and MLFlow `npm run start:observe` (it runs ./src/agent_observe.ts file). The output of the `curl` command is saved in the **./tmp/observe/trace.json** file
+2. Start the agent using the observe and MLFlow `npm run start:observe` (it runs the `./src/agent_observe.ts` file).
+3. Run the `curl` command that retrieves data from Bee Observe and passes them to the `MLFlow` instance.
+4. Access MLFlow web application [`http://localhost:8080/#/experiments/`](http://localhost:8080/#/experiments/)
+   - Credentials: (user: `admin`, password: `password`)

src/agent_observe.ts

@@ -56,15 +56,16 @@ try {
             console.error(`Agent 🤖 : `, ObserveError.ensure(err).explain());
           } else {
             const { id, response } = data?.result || {};
-            console.log(`Agent 🤖 : `, response?.text || "Invalid output");
+            console.info(`Observe 🔎 : `, response?.text || "Invalid output");
 
             // you can use `&include_mlflow_tree=true` as well to return all sent data to mlflow
-            console.log(
-              `Agent 🤖 : Call the Observe API via this curl command outside of this Interactive session and see the trace data in the "trace.json" file: \n\n`,
+            console.info(
+              `Observe 🔎 : Call the Observe API via this curl command outside of this Interactive session and see the trace data in the "trace.json" file: \n\n`,
               `curl -X GET "${beeObserveApiSetting.baseUrl}/trace/${id}?include_tree=true&include_mlflow=true" \\
 \t-H "x-bee-authorization: ${beeObserveApiSetting.apiAuthKey}" \\
 \t-H "Content-Type: application/json" \\
-\t-o tmp/observe/trace.json`,
+\t-o ${process.cwd()}/tmp/observe/trace.json`,
+              `\n`,
             );
           }
         },