This commit is contained in:
adilhafeez 2026-03-19 00:59:30 +00:00
parent 4bc5d92f7e
commit 2c78420371
34 changed files with 165 additions and 76 deletions

View file

@ -227,7 +227,7 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
</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-61"><span class="linenos"> 61</span><span class="w"> </span><span class="nt">input_filters</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>
@ -235,46 +235,49 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
</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-69"><span class="linenos"> 69</span><span class="w"> </span><span class="c1"># Optional: attach input filters for guardrails on direct LLM requests</span>
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="c1"># input_filters:</span>
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="c1"># - input_guards</span>
</span><span id="line-72"><span class="linenos"> 72</span>
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
</span><span id="line-74"><span class="linenos"> 74</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-75"><span class="linenos"> 75</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-76"><span class="linenos"> 76</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-77"><span class="linenos"> 77</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-78"><span class="linenos"> 78</span><span class="w"> </span><span class="c1"># This listener is used for prompt_targets and function calling</span>
</span><span id="line-79"><span class="linenos"> 79</span>
</span><span id="line-80"><span class="linenos"> 80</span><span class="c1"># Reusable service endpoints</span>
</span><span id="line-81"><span class="linenos"> 81</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="nt">app_server</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">127.0.0.1:80</span>
</span><span id="line-84"><span class="linenos"> 84</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-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>
</span><span id="line-88"><span class="linenos"> 88</span><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">get_current_weather</span>
</span><span id="line-89"><span class="linenos"> 89</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">Get current weather at a location.</span>
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-91"><span class="linenos"> 91</span><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">location</span>
</span><span id="line-92"><span class="linenos"> 92</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">The location to get the weather for</span>
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-94"><span class="linenos"> 94</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">string</span>
</span><span id="line-95"><span class="linenos"> 95</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
</span><span id="line-96"><span class="linenos"> 96</span><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">days</span>
</span><span id="line-97"><span class="linenos"> 97</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">the number of days for the request</span>
</span><span id="line-98"><span class="linenos"> 98</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-99"><span class="linenos"> 99</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">int</span>
</span><span id="line-100"><span class="linenos">100</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-101"><span class="linenos">101</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">app_server</span>
</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 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><span id="line-86"><span class="linenos"> 86</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
</span><span id="line-87"><span class="linenos"> 87</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-88"><span class="linenos"> 88</span>
</span><span id="line-89"><span class="linenos"> 89</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
</span><span id="line-90"><span class="linenos"> 90</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-91"><span class="linenos"> 91</span><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">get_current_weather</span>
</span><span id="line-92"><span class="linenos"> 92</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">Get current weather at a location.</span>
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-94"><span class="linenos"> 94</span><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">location</span>
</span><span id="line-95"><span class="linenos"> 95</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">The location to get the weather for</span>
</span><span id="line-96"><span class="linenos"> 96</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-97"><span class="linenos"> 97</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">string</span>
</span><span id="line-98"><span class="linenos"> 98</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
</span><span id="line-99"><span class="linenos"> 99</span><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">days</span>
</span><span id="line-100"><span class="linenos">100</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">the number of days for the request</span>
</span><span id="line-101"><span class="linenos">101</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-102"><span class="linenos">102</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">int</span>
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-104"><span class="linenos">104</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">app_server</span>
</span><span id="line-105"><span class="linenos">105</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-106"><span class="linenos">106</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-107"><span class="linenos">107</span>
</span><span id="line-108"><span class="linenos">108</span><span class="c1"># OpenTelemetry tracing configuration</span>
</span><span id="line-109"><span class="linenos">109</span><span class="nt">tracing</span><span class="p">:</span>
</span><span id="line-110"><span class="linenos">110</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
</span><span id="line-111"><span class="linenos">111</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>
@ -302,7 +305,7 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
</div><footer class="py-6 border-t border-border md:py-0">
<div class="container flex flex-col items-center justify-between gap-4 md:h-24 md:flex-row">
<div class="flex flex-col items-center gap-4 px-8 md:flex-row md:gap-2 md:px-0">
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Mar 16, 2026. </p>
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Mar 19, 2026. </p>
</div>
</div>
</footer>