apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-28 18:36:34 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

debug streaming

Browse source 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
This commit is contained in:
José Ulises Niño Rivera 2024-10-13 15:36:53 -06:00
parent 639839fbb1
commit bbd6058ca0
5 changed files with 122 additions and 230 deletions
Download patch file Download diff file Expand all files Collapse all files

81
arch/envoy.template.yaml
View file

@ -174,87 +174,6 @@ static_resources:
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
- name: arch_listener_llm
address:
socket_address:
address: 0.0.0.0
port_value: 12000
filter_chains:
- filters:
- name: envoy.filters.network.http_connection_manager
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
{% if "random_sampling" in arch_tracing and arch_tracing["random_sampling"] > 0 %}
generate_request_id: true
tracing:
provider:
name: envoy.tracers.opentelemetry
typed_config:
"@type": type.googleapis.com/envoy.config.trace.v3.OpenTelemetryConfig
grpc_service:
envoy_grpc:
cluster_name: opentelemetry_collector
timeout: 0.250s
service_name: arch
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_listener_http
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
access_log:
- name: envoy.access_loggers.file
typed_config:
"@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
path: "/var/log/access_llm.log"
route_config:
name: local_routes
virtual_hosts:
- name: local_service
domains:
- "*"
routes:
{% for provider in arch_llm_providers %}
- match:
prefix: "/"
headers:
- name: "x-arch-llm-provider"
string_match:
exact: {{ provider.name }}
route:
auto_host_rewrite: true
cluster: {{ provider.provider }}
timeout: 60s
{% endfor %}
- match:
prefix: "/"
direct_response:
status: 400
body:
inline_string: "x-arch-llm-provider header not set, cannot perform routing\n"
http_filters:
- name: envoy.filters.http.wasm
typed_config:
"@type": type.googleapis.com/udpa.type.v1.TypedStruct
type_url: type.googleapis.com/envoy.extensions.filters.http.wasm.v3.Wasm
value:
config:
name: "http_config"
root_id: llm_gateway
configuration:
"@type": "type.googleapis.com/google.protobuf.StringValue"
value: |
{{ arch_llm_config | indent(32) }}
vm_config:
runtime: "envoy.wasm.runtime.v8"
code:
local:
filename: "/etc/envoy/proxy-wasm-plugins/intelligent_prompt_gateway.wasm"
- name: envoy.filters.http.router
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
clusters:
- name: openai
connect_timeout: 5s