phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 10:42:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixes

Browse source
This commit is contained in:
Hardik Shah 2025-01-23 12:11:14 -08:00
parent 86466b71a9
commit cb41f2674c
2 changed files with 11 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/building_applications/agent_execution_loop.md
View file

@ -1,4 +1,4 @@
# Agent Execution Loop ## Agent Execution Loop
Agents are the heart of complex AI applications. They combine inference, memory, safety, and tool usage into coherent workflows. At its core, an agent follows a sophisticated execution loop that enables multi-step reasoning, tool usage, and safety checks. Agents are the heart of complex AI applications. They combine inference, memory, safety, and tool usage into coherent workflows. At its core, an agent follows a sophisticated execution loop that enables multi-step reasoning, tool usage, and safety checks.

21
docs/source/building_applications/telemetry.md
View file

@ -1,11 +1,10 @@
# Telemetry ## Telemetry
The Llama Stack telemetry system provides comprehensive tracing, metrics, and logging capabilities. It supports multiple sink types including OpenTelemetry, SQLite, and Console output. The Llama Stack telemetry system provides comprehensive tracing, metrics, and logging capabilities. It supports multiple sink types including OpenTelemetry, SQLite, and Console output.
## Key Concepts #### Key Concepts
### Events #### Events
The telemetry system supports three main types of events: The telemetry system supports three main types of events:
- **Unstructured Log Events**: Free-form log messages with severity levels - **Unstructured Log Events**: Free-form log messages with severity levels
@ -31,24 +30,24 @@ structured_log_event = SpanStartPayload(
) )
``` ```
### Spans and Traces #### Spans and Traces
- **Spans**: Represent operations with timing and hierarchical relationships - **Spans**: Represent operations with timing and hierarchical relationships
- **Traces**: Collection of related spans forming a complete request flow - **Traces**: Collection of related spans forming a complete request flow
### Sinks #### Sinks
- **OpenTelemetry**: Send events to an OpenTelemetry Collector. This is useful for visualizing traces in a tool like Jaeger. - **OpenTelemetry**: Send events to an OpenTelemetry Collector. This is useful for visualizing traces in a tool like Jaeger.
- **SQLite**: Store events in a local SQLite database. This is needed if you want to query the events later through the Llama Stack API. - **SQLite**: Store events in a local SQLite database. This is needed if you want to query the events later through the Llama Stack API.
- **Console**: Print events to the console. - **Console**: Print events to the console.
## Providers #### Providers
### Meta-Reference Provider #### Meta-Reference Provider
Currently, only the meta-reference provider is implemented. It can be configured to send events to three sink types: Currently, only the meta-reference provider is implemented. It can be configured to send events to three sink types:
1) OpenTelemetry Collector 1) OpenTelemetry Collector
2) SQLite 2) SQLite
3) Console 3) Console
## Configuration #### Configuration
Here's an example that sends telemetry signals to all three sink types. Your configuration might use only one. Here's an example that sends telemetry signals to all three sink types. Your configuration might use only one.
```yaml ```yaml
@ -61,7 +60,7 @@ Here's an example that sends telemetry signals to all three sink types. Your con
sqlite_db_path: "/path/to/telemetry.db" sqlite_db_path: "/path/to/telemetry.db"
``` ```
## Jaeger to visualize traces #### Jaeger to visualize traces
The `otel` sink works with any service compatible with the OpenTelemetry collector. Let's use Jaeger to visualize this data. The `otel` sink works with any service compatible with the OpenTelemetry collector. Let's use Jaeger to visualize this data.
@ -75,6 +74,6 @@ $ docker run --rm --name jaeger \
Once the Jaeger instance is running, you can visualize traces by navigating to http://localhost:16686/. Once the Jaeger instance is running, you can visualize traces by navigating to http://localhost:16686/.
## Querying Traces Stored in SQLIte #### Querying Traces Stored in SQLIte
The `sqlite` sink allows you to query traces without an external system. Here are some example queries. Refer to the notebook at [Llama Stack Building AI Applications](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb) for more examples on how to query traces and spaces. The `sqlite` sink allows you to query traces without an external system. Here are some example queries. Refer to the notebook at [Llama Stack Building AI Applications](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb) for more examples on how to query traces and spaces.