mirror of
https://github.com/katanemo/plano.git
synced 2026-06-08 14:55:14 +02:00
deploy: 4d53297c17
This commit is contained in:
salmanap
parent
be238fcaef
commit
670388c0bb
6 changed files with 233 additions and 106 deletions
|
|
@ -1,26 +1,22 @@
|
|||
|
||||
# Arch Gateway configuration version
|
||||
version: v0.3.0
|
||||
|
||||
|
||||
# External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)
|
||||
agents:
|
||||
- id: weather_agent # Example agent for weather
|
||||
- id: weather_agent # Example agent for weather
|
||||
url: http://host.docker.internal:10510
|
||||
|
||||
- id: flight_agent # Example agent for flights
|
||||
- id: flight_agent # Example agent for flights
|
||||
url: http://host.docker.internal:10520
|
||||
|
||||
|
||||
# MCP filters applied to requests/responses (e.g., input validation, query rewriting)
|
||||
filters:
|
||||
- id: input_guards # Example filter for input validation
|
||||
- id: input_guards # Example filter for input validation
|
||||
url: http://host.docker.internal:10500
|
||||
# type: mcp (default)
|
||||
# transport: streamable-http (default)
|
||||
# tool: input_guards (default - same as filter id)
|
||||
|
||||
|
||||
# LLM provider configurations with API keys and model routing
|
||||
model_providers:
|
||||
- model: openai/gpt-4o
|
||||
|
|
@ -36,6 +32,12 @@ model_providers:
|
|||
- model: mistral/ministral-3b-latest
|
||||
access_key: $MISTRAL_API_KEY
|
||||
|
||||
# Example: Passthrough authentication for LiteLLM or similar proxies
|
||||
# When passthrough_auth is true, client's Authorization header is forwarded
|
||||
# instead of using the configured access_key
|
||||
- model: openai/gpt-4o-litellm
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
|
||||
# Model aliases - use friendly names instead of full provider model names
|
||||
model_aliases:
|
||||
|
|
@ -45,7 +47,6 @@ model_aliases:
|
|||
smart-llm:
|
||||
target: gpt-4o
|
||||
|
||||
|
||||
# HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access
|
||||
listeners:
|
||||
# Agent listener for routing requests to multiple agents
|
||||
|
|
@ -73,7 +74,6 @@ listeners:
|
|||
port: 10000
|
||||
# This listener is used for prompt_targets and function calling
|
||||
|
||||
|
||||
# Reusable service endpoints
|
||||
endpoints:
|
||||
app_server:
|
||||
|
|
@ -83,7 +83,6 @@ endpoints:
|
|||
mistral_local:
|
||||
endpoint: 127.0.0.1:8001
|
||||
|
||||
|
||||
# Prompt targets for function calling and API orchestration
|
||||
prompt_targets:
|
||||
- name: get_current_weather
|
||||
|
|
@ -103,7 +102,6 @@ prompt_targets:
|
|||
path: /weather
|
||||
http_method: POST
|
||||
|
||||
|
||||
# OpenTelemetry tracing configuration
|
||||
tracing:
|
||||
# Random sampling percentage (1-100)
|
||||
|
|
|
|||
|
|
@ -893,6 +893,67 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="passthrough-authentication">
|
||||
<span id="passthrough-auth"></span><h3>Passthrough Authentication<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#passthrough-authentication" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#passthrough-authentication'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||||
<p>When deploying Plano in front of LLM proxy services that manage their own API key validation (such as LiteLLM, OpenRouter, or custom gateways), you may want to forward the client’s original <code class="docutils literal notranslate"><span class="pre">Authorization</span></code> header instead of replacing it with a configured <code class="docutils literal notranslate"><span class="pre">access_key</span></code>.</p>
|
||||
<p>The <code class="docutils literal notranslate"><span class="pre">passthrough_auth</span></code> option enables this behavior:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="c1"># Forward client's Authorization header to LiteLLM</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-litellm</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-7">
|
||||
</span><span id="line-8"><span class="w"> </span><span class="c1"># Forward to OpenRouter</span>
|
||||
</span><span id="line-9"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/claude-3-opus</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://openrouter.ai/api/v1</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<p><strong>How it works:</strong></p>
|
||||
<ol class="arabic simple">
|
||||
<li><p>Client sends a request with <code class="docutils literal notranslate"><span class="pre">Authorization:</span> <span class="pre">Bearer</span> <span class="pre"><virtual-key></span></code></p></li>
|
||||
<li><p>Plano preserves this header instead of replacing it with <code class="docutils literal notranslate"><span class="pre">access_key</span></code></p></li>
|
||||
<li><p>The upstream service (e.g., LiteLLM) validates the virtual key</p></li>
|
||||
<li><p>Response flows back through Plano to the client</p></li>
|
||||
</ol>
|
||||
<p><strong>Use Cases:</strong></p>
|
||||
<ul class="simple">
|
||||
<li><p><strong>LiteLLM Integration</strong>: Route requests to LiteLLM which manages virtual keys and rate limits</p></li>
|
||||
<li><p><strong>OpenRouter</strong>: Forward requests to OpenRouter with per-user API keys</p></li>
|
||||
<li><p><strong>Custom API Gateways</strong>: Integrate with internal gateways that have their own authentication</p></li>
|
||||
<li><p><strong>Multi-tenant Deployments</strong>: Allow different clients to use their own credentials</p></li>
|
||||
</ul>
|
||||
<p><strong>Important Notes:</strong></p>
|
||||
<ul class="simple">
|
||||
<li><p>When <code class="docutils literal notranslate"><span class="pre">passthrough_auth:</span> <span class="pre">true</span></code> is set, the <code class="docutils literal notranslate"><span class="pre">access_key</span></code> field is ignored (a warning is logged if both are configured)</p></li>
|
||||
<li><p>If the client doesn’t provide an <code class="docutils literal notranslate"><span class="pre">Authorization</span></code> header, the request is forwarded without authentication (upstream will likely return 401)</p></li>
|
||||
<li><p>The <code class="docutils literal notranslate"><span class="pre">base_url</span></code> is typically required when using <code class="docutils literal notranslate"><span class="pre">passthrough_auth</span></code></p></li>
|
||||
</ul>
|
||||
<p><strong>Configuration with LiteLLM example:</strong></p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># plano_config.yaml</span>
|
||||
</span><span id="line-2"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.3.0</span>
|
||||
</span><span id="line-3">
|
||||
</span><span id="line-4"><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">llm</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-8">
|
||||
</span><span id="line-9"><span class="nt">model_providers</span><span class="p">:</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># Client request - virtual key is forwarded to upstream</span>
|
||||
</span><span id="line-2">curl<span class="w"> </span>http://localhost:10000/v1/chat/completions<span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-3"><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Authorization: Bearer sk-litellm-virtual-key-abc123"</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-4"><span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-5"><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="model-selection-guidelines">
|
||||
<h2>Model Selection Guidelines<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#model-selection-guidelines" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#model-selection-guidelines'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
|
|
@ -966,6 +1027,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<li><a :data-current="activeSection === '#multiple-provider-instances'" class="reference internal" href="#multiple-provider-instances">Multiple Provider Instances</a></li>
|
||||
<li><a :data-current="activeSection === '#default-model-configuration'" class="reference internal" href="#default-model-configuration">Default Model Configuration</a></li>
|
||||
<li><a :data-current="activeSection === '#routing-preferences'" class="reference internal" href="#routing-preferences">Routing Preferences</a></li>
|
||||
<li><a :data-current="activeSection === '#passthrough-authentication'" class="reference internal" href="#passthrough-authentication">Passthrough Authentication</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><a :data-current="activeSection === '#model-selection-guidelines'" class="reference internal" href="#model-selection-guidelines">Model Selection Guidelines</a></li>
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
Plano Docs v0.4.2
|
||||
llms.txt (auto-generated)
|
||||
Generated (UTC): 2026-01-14T19:37:47.390683+00:00
|
||||
Generated (UTC): 2026-01-14T23:06:59.315217+00:00
|
||||
|
||||
Table of contents
|
||||
- Agents (concepts/agents)
|
||||
|
|
@ -1956,6 +1956,76 @@ llm_providers:
|
|||
- name: creative_writing
|
||||
description: creative content generation, storytelling, and writing assistance
|
||||
|
||||
|
||||
|
||||
Passthrough Authentication
|
||||
|
||||
When deploying Plano in front of LLM proxy services that manage their own API key validation (such as LiteLLM, OpenRouter, or custom gateways), you may want to forward the client’s original Authorization header instead of replacing it with a configured access_key.
|
||||
|
||||
The passthrough_auth option enables this behavior:
|
||||
|
||||
llm_providers:
|
||||
# Forward client's Authorization header to LiteLLM
|
||||
- model: openai/gpt-4o-litellm
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
default: true
|
||||
|
||||
# Forward to OpenRouter
|
||||
- model: openai/claude-3-opus
|
||||
base_url: https://openrouter.ai/api/v1
|
||||
passthrough_auth: true
|
||||
|
||||
How it works:
|
||||
|
||||
Client sends a request with Authorization: Bearer <virtual-key>
|
||||
|
||||
Plano preserves this header instead of replacing it with access_key
|
||||
|
||||
The upstream service (e.g., LiteLLM) validates the virtual key
|
||||
|
||||
Response flows back through Plano to the client
|
||||
|
||||
Use Cases:
|
||||
|
||||
LiteLLM Integration: Route requests to LiteLLM which manages virtual keys and rate limits
|
||||
|
||||
OpenRouter: Forward requests to OpenRouter with per-user API keys
|
||||
|
||||
Custom API Gateways: Integrate with internal gateways that have their own authentication
|
||||
|
||||
Multi-tenant Deployments: Allow different clients to use their own credentials
|
||||
|
||||
Important Notes:
|
||||
|
||||
When passthrough_auth: true is set, the access_key field is ignored (a warning is logged if both are configured)
|
||||
|
||||
If the client doesn’t provide an Authorization header, the request is forwarded without authentication (upstream will likely return 401)
|
||||
|
||||
The base_url is typically required when using passthrough_auth
|
||||
|
||||
Configuration with LiteLLM example:
|
||||
|
||||
# plano_config.yaml
|
||||
version: v0.3.0
|
||||
|
||||
listeners:
|
||||
- name: llm
|
||||
type: model
|
||||
port: 10000
|
||||
|
||||
model_providers:
|
||||
- model: openai/gpt-4o
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
default: true
|
||||
|
||||
# Client request - virtual key is forwarded to upstream
|
||||
curl http://localhost:10000/v1/chat/completions \
|
||||
-H "Authorization: Bearer sk-litellm-virtual-key-abc123" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
|
||||
|
||||
Model Selection Guidelines
|
||||
|
||||
For Production Applications:
|
||||
|
|
@ -5424,29 +5494,25 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
|
|||
|
||||
Plano Configuration - Full Reference
|
||||
|
||||
|
||||
# Arch Gateway configuration version
|
||||
version: v0.3.0
|
||||
|
||||
|
||||
# External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)
|
||||
agents:
|
||||
- id: weather_agent # Example agent for weather
|
||||
- id: weather_agent # Example agent for weather
|
||||
url: http://host.docker.internal:10510
|
||||
|
||||
- id: flight_agent # Example agent for flights
|
||||
- id: flight_agent # Example agent for flights
|
||||
url: http://host.docker.internal:10520
|
||||
|
||||
|
||||
# MCP filters applied to requests/responses (e.g., input validation, query rewriting)
|
||||
filters:
|
||||
- id: input_guards # Example filter for input validation
|
||||
- id: input_guards # Example filter for input validation
|
||||
url: http://host.docker.internal:10500
|
||||
# type: mcp (default)
|
||||
# transport: streamable-http (default)
|
||||
# tool: input_guards (default - same as filter id)
|
||||
|
||||
|
||||
# LLM provider configurations with API keys and model routing
|
||||
model_providers:
|
||||
- model: openai/gpt-4o
|
||||
|
|
@ -5462,6 +5528,12 @@ model_providers:
|
|||
- model: mistral/ministral-3b-latest
|
||||
access_key: $MISTRAL_API_KEY
|
||||
|
||||
# Example: Passthrough authentication for LiteLLM or similar proxies
|
||||
# When passthrough_auth is true, client's Authorization header is forwarded
|
||||
# instead of using the configured access_key
|
||||
- model: openai/gpt-4o-litellm
|
||||
base_url: https://litellm.example.com
|
||||
passthrough_auth: true
|
||||
|
||||
# Model aliases - use friendly names instead of full provider model names
|
||||
model_aliases:
|
||||
|
|
@ -5471,7 +5543,6 @@ model_aliases:
|
|||
smart-llm:
|
||||
target: gpt-4o
|
||||
|
||||
|
||||
# HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access
|
||||
listeners:
|
||||
# Agent listener for routing requests to multiple agents
|
||||
|
|
@ -5499,7 +5570,6 @@ listeners:
|
|||
port: 10000
|
||||
# This listener is used for prompt_targets and function calling
|
||||
|
||||
|
||||
# Reusable service endpoints
|
||||
endpoints:
|
||||
app_server:
|
||||
|
|
@ -5509,7 +5579,6 @@ endpoints:
|
|||
mistral_local:
|
||||
endpoint: 127.0.0.1:8001
|
||||
|
||||
|
||||
# Prompt targets for function calling and API orchestration
|
||||
prompt_targets:
|
||||
- name: get_current_weather
|
||||
|
|
@ -5529,7 +5598,6 @@ prompt_targets:
|
|||
path: /weather
|
||||
http_method: POST
|
||||
|
||||
|
||||
# OpenTelemetry tracing configuration
|
||||
tracing:
|
||||
# Random sampling percentage (1-100)
|
||||
|
|
|
|||
BIN
objects.inv
BIN
objects.inv
Binary file not shown.
|
|
@ -167,87 +167,87 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
|
|||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="c1"># Arch Gateway configuration version</span>
|
||||
</span><span id="line-2"><span class="linenos"> 2</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.3.0</span>
|
||||
</span><span id="line-3"><span class="linenos"> 3</span>
|
||||
</span><span id="line-4"><span class="linenos"> 4</span>
|
||||
</span><span id="line-5"><span class="linenos"> 5</span><span class="c1"># External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)</span>
|
||||
</span><span id="line-6"><span class="linenos"> 6</span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">weather_agent</span><span class="w"> </span><span class="c1"># Example agent for weather</span>
|
||||
</span><span id="line-8"><span class="linenos"> 8</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10510</span>
|
||||
</span><span id="line-9"><span class="linenos"> 9</span>
|
||||
</span><span id="line-10"><span class="linenos"> 10</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">flight_agent</span><span class="w"> </span><span class="c1"># Example agent for flights</span>
|
||||
</span><span id="line-11"><span class="linenos"> 11</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10520</span>
|
||||
</span><span id="line-12"><span class="linenos"> 12</span>
|
||||
</span><span id="line-13"><span class="linenos"> 13</span>
|
||||
</span><span id="line-14"><span class="linenos"> 14</span><span class="c1"># MCP filters applied to requests/responses (e.g., input validation, query rewriting)</span>
|
||||
</span><span id="line-15"><span class="linenos"> 15</span><span class="nt">filters</span><span class="p">:</span>
|
||||
</span><span id="line-16"><span class="linenos"> 16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span><span class="w"> </span><span class="c1"># Example filter for input validation</span>
|
||||
</span><span id="line-17"><span class="linenos"> 17</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10500</span>
|
||||
</span><span id="line-18"><span class="linenos"> 18</span><span class="w"> </span><span class="c1"># type: mcp (default)</span>
|
||||
</span><span id="line-19"><span class="linenos"> 19</span><span class="w"> </span><span class="c1"># transport: streamable-http (default)</span>
|
||||
</span><span id="line-20"><span class="linenos"> 20</span><span class="w"> </span><span class="c1"># tool: input_guards (default - same as filter id)</span>
|
||||
</span><span id="line-21"><span class="linenos"> 21</span>
|
||||
</span><span id="line-22"><span class="linenos"> 22</span>
|
||||
</span><span id="line-23"><span class="linenos"> 23</span><span class="c1"># LLM provider configurations with API keys and model routing</span>
|
||||
</span><span id="line-24"><span class="linenos"> 24</span><span class="nt">model_providers</span><span class="p">:</span>
|
||||
</span><span id="line-25"><span class="linenos"> 25</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-26"><span class="linenos"> 26</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-27"><span class="linenos"> 27</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-4"><span class="linenos"> 4</span><span class="c1"># External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)</span>
|
||||
</span><span id="line-5"><span class="linenos"> 5</span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-6"><span class="linenos"> 6</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">weather_agent</span><span class="w"> </span><span class="c1"># Example agent for weather</span>
|
||||
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10510</span>
|
||||
</span><span id="line-8"><span class="linenos"> 8</span>
|
||||
</span><span id="line-9"><span class="linenos"> 9</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">flight_agent</span><span class="w"> </span><span class="c1"># Example agent for flights</span>
|
||||
</span><span id="line-10"><span class="linenos"> 10</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10520</span>
|
||||
</span><span id="line-11"><span class="linenos"> 11</span>
|
||||
</span><span id="line-12"><span class="linenos"> 12</span><span class="c1"># MCP filters applied to requests/responses (e.g., input validation, query rewriting)</span>
|
||||
</span><span id="line-13"><span class="linenos"> 13</span><span class="nt">filters</span><span class="p">:</span>
|
||||
</span><span id="line-14"><span class="linenos"> 14</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span><span class="w"> </span><span class="c1"># Example filter for input validation</span>
|
||||
</span><span id="line-15"><span class="linenos"> 15</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10500</span>
|
||||
</span><span id="line-16"><span class="linenos"> 16</span><span class="w"> </span><span class="c1"># type: mcp (default)</span>
|
||||
</span><span id="line-17"><span class="linenos"> 17</span><span class="w"> </span><span class="c1"># transport: streamable-http (default)</span>
|
||||
</span><span id="line-18"><span class="linenos"> 18</span><span class="w"> </span><span class="c1"># tool: input_guards (default - same as filter id)</span>
|
||||
</span><span id="line-19"><span class="linenos"> 19</span>
|
||||
</span><span id="line-20"><span class="linenos"> 20</span><span class="c1"># LLM provider configurations with API keys and model routing</span>
|
||||
</span><span id="line-21"><span class="linenos"> 21</span><span class="nt">model_providers</span><span class="p">:</span>
|
||||
</span><span id="line-22"><span class="linenos"> 22</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-23"><span class="linenos"> 23</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-24"><span class="linenos"> 24</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-25"><span class="linenos"> 25</span>
|
||||
</span><span id="line-26"><span class="linenos"> 26</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
|
||||
</span><span id="line-27"><span class="linenos"> 27</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-28"><span class="linenos"> 28</span>
|
||||
</span><span id="line-29"><span class="linenos"> 29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
|
||||
</span><span id="line-30"><span class="linenos"> 30</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-29"><span class="linenos"> 29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-0</span>
|
||||
</span><span id="line-30"><span class="linenos"> 30</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-31"><span class="linenos"> 31</span>
|
||||
</span><span id="line-32"><span class="linenos"> 32</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-0</span>
|
||||
</span><span id="line-33"><span class="linenos"> 33</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-32"><span class="linenos"> 32</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">mistral/ministral-3b-latest</span>
|
||||
</span><span id="line-33"><span class="linenos"> 33</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_API_KEY</span>
|
||||
</span><span id="line-34"><span class="linenos"> 34</span>
|
||||
</span><span id="line-35"><span class="linenos"> 35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">mistral/ministral-3b-latest</span>
|
||||
</span><span id="line-36"><span class="linenos"> 36</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_API_KEY</span>
|
||||
</span><span id="line-37"><span class="linenos"> 37</span>
|
||||
</span><span id="line-38"><span class="linenos"> 38</span>
|
||||
</span><span id="line-39"><span class="linenos"> 39</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
|
||||
</span><span id="line-40"><span class="linenos"> 40</span><span class="nt">model_aliases</span><span class="p">:</span>
|
||||
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
|
||||
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
|
||||
</span><span id="line-43"><span class="linenos"> 43</span>
|
||||
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
|
||||
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-35"><span class="linenos"> 35</span><span class="w"> </span><span class="c1"># Example: Passthrough authentication for LiteLLM or similar proxies</span>
|
||||
</span><span id="line-36"><span class="linenos"> 36</span><span class="w"> </span><span class="c1"># When passthrough_auth is true, client's Authorization header is forwarded</span>
|
||||
</span><span id="line-37"><span class="linenos"> 37</span><span class="w"> </span><span class="c1"># instead of using the configured access_key</span>
|
||||
</span><span id="line-38"><span class="linenos"> 38</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-litellm</span>
|
||||
</span><span id="line-39"><span class="linenos"> 39</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">https://litellm.example.com</span>
|
||||
</span><span id="line-40"><span class="linenos"> 40</span><span class="w"> </span><span class="nt">passthrough_auth</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-41"><span class="linenos"> 41</span>
|
||||
</span><span id="line-42"><span class="linenos"> 42</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
|
||||
</span><span id="line-43"><span class="linenos"> 43</span><span class="nt">model_aliases</span><span class="p">:</span>
|
||||
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
|
||||
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
|
||||
</span><span id="line-46"><span class="linenos"> 46</span>
|
||||
</span><span id="line-47"><span class="linenos"> 47</span>
|
||||
</span><span id="line-48"><span class="linenos"> 48</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
|
||||
</span><span id="line-49"><span class="linenos"> 49</span><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
|
||||
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">agent</span>
|
||||
</span><span id="line-52"><span class="linenos"> 52</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">travel_booking_service</span>
|
||||
</span><span id="line-53"><span class="linenos"> 53</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8001</span>
|
||||
</span><span id="line-54"><span class="linenos"> 54</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
|
||||
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
|
||||
</span><span id="line-58"><span class="linenos"> 58</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">virtual assistant for retrieval augmented generation tasks</span>
|
||||
</span><span id="line-59"><span class="linenos"> 59</span><span class="w"> </span><span class="nt">filter_chain</span><span class="p">:</span>
|
||||
</span><span id="line-60"><span class="linenos"> 60</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
|
||||
</span><span id="line-61"><span class="linenos"> 61</span>
|
||||
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
|
||||
</span><span id="line-63"><span class="linenos"> 63</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
|
||||
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model_1</span>
|
||||
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-66"><span class="linenos"> 66</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
|
||||
</span><span id="line-67"><span class="linenos"> 67</span>
|
||||
</span><span id="line-68"><span class="linenos"> 68</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
|
||||
</span><span id="line-69"><span class="linenos"> 69</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt</span>
|
||||
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt_function_listener</span>
|
||||
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="c1"># This listener is used for prompt_targets and function calling</span>
|
||||
</span><span id="line-74"><span class="linenos"> 74</span>
|
||||
</span><span id="line-75"><span class="linenos"> 75</span>
|
||||
</span><span id="line-76"><span class="linenos"> 76</span><span class="c1"># Reusable service endpoints</span>
|
||||
</span><span id="line-77"><span class="linenos"> 77</span><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-78"><span class="linenos"> 78</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-80"><span class="linenos"> 80</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span><span id="line-81"><span class="linenos"> 81</span>
|
||||
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
|
||||
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
|
||||
</span><span id="line-84"><span class="linenos"> 84</span>
|
||||
</span><span id="line-47"><span class="linenos"> 47</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
|
||||
</span><span id="line-48"><span class="linenos"> 48</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-49"><span class="linenos"> 49</span>
|
||||
</span><span id="line-50"><span class="linenos"> 50</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
|
||||
</span><span id="line-51"><span class="linenos"> 51</span><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-52"><span class="linenos"> 52</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
|
||||
</span><span id="line-53"><span class="linenos"> 53</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">agent</span>
|
||||
</span><span id="line-54"><span class="linenos"> 54</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">travel_booking_service</span>
|
||||
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8001</span>
|
||||
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
|
||||
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-58"><span class="linenos"> 58</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-59"><span class="linenos"> 59</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
|
||||
</span><span id="line-60"><span class="linenos"> 60</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">virtual assistant for retrieval augmented generation tasks</span>
|
||||
</span><span id="line-61"><span class="linenos"> 61</span><span class="w"> </span><span class="nt">filter_chain</span><span class="p">:</span>
|
||||
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
|
||||
</span><span id="line-63"><span class="linenos"> 63</span>
|
||||
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
|
||||
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model</span>
|
||||
</span><span id="line-66"><span class="linenos"> 66</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">model_1</span>
|
||||
</span><span id="line-67"><span class="linenos"> 67</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-68"><span class="linenos"> 68</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
|
||||
</span><span id="line-69"><span class="linenos"> 69</span>
|
||||
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
|
||||
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt</span>
|
||||
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompt_function_listener</span>
|
||||
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-74"><span class="linenos"> 74</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-75"><span class="linenos"> 75</span><span class="w"> </span><span class="c1"># This listener is used for prompt_targets and function calling</span>
|
||||
</span><span id="line-76"><span class="linenos"> 76</span>
|
||||
</span><span id="line-77"><span class="linenos"> 77</span><span class="c1"># Reusable service endpoints</span>
|
||||
</span><span id="line-78"><span class="linenos"> 78</span><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-80"><span class="linenos"> 80</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-81"><span class="linenos"> 81</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span><span id="line-82"><span class="linenos"> 82</span>
|
||||
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
|
||||
</span><span id="line-84"><span class="linenos"> 84</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
|
||||
</span><span id="line-85"><span class="linenos"> 85</span>
|
||||
</span><span id="line-86"><span class="linenos"> 86</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
|
||||
</span><span id="line-87"><span class="linenos"> 87</span><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
|
|
@ -268,11 +268,10 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
|
|||
</span><span id="line-102"><span class="linenos">102</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/weather</span>
|
||||
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
|
||||
</span><span id="line-104"><span class="linenos">104</span>
|
||||
</span><span id="line-105"><span class="linenos">105</span>
|
||||
</span><span id="line-106"><span class="linenos">106</span><span class="c1"># OpenTelemetry tracing configuration</span>
|
||||
</span><span id="line-107"><span class="linenos">107</span><span class="nt">tracing</span><span class="p">:</span>
|
||||
</span><span id="line-108"><span class="linenos">108</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
|
||||
</span><span id="line-109"><span class="linenos">109</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
|
||||
</span><span id="line-105"><span class="linenos">105</span><span class="c1"># OpenTelemetry tracing configuration</span>
|
||||
</span><span id="line-106"><span class="linenos">106</span><span class="nt">tracing</span><span class="p">:</span>
|
||||
</span><span id="line-107"><span class="linenos">107</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
|
||||
</span><span id="line-108"><span class="linenos">108</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
Loading…
Add table
Add a link
Reference in a new issue