apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-07-23 16:51:04 +02:00
Code Issues Projects Releases Packages Wiki Activity

use ingress/egress

Browse source
This commit is contained in:
Adil Hafeez 2025-02-14 16:43:51 -08:00
parent 4a957f2b86
commit 136daa2d3c
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
18 changed files with 31 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

7
arch/arch_config_schema.yaml
View file

@ -5,8 +5,9 @@ properties:
type: string type: string
listeners: listeners:
type: object type: object
additionalProperties: false
properties: properties:
prompt_gateway: ingress_traffic:
type: object type: object
properties: properties:
address: address:
@ -20,7 +21,7 @@ properties:
timeout: timeout:
type: string type: string
additionalProperties: false additionalProperties: false
llm_gateway: egress_traffic:
type: object type: object
properties: properties:
address: address:
@ -31,7 +32,6 @@ properties:
type: string type: string
enum: enum:
- openai - openai
- huggingface
timeout: timeout:
type: string type: string
additionalProperties: false additionalProperties: false
@ -247,5 +247,4 @@ properties:
additionalProperties: false additionalProperties: false
required: required:
- version - version
- listeners
- llm_providers - llm_providers

6
arch/tools/cli/config_generator.py
View file

@ -104,7 +104,9 @@ def validate_and_render_schema():
arch_config_string = yaml.dump(config_yaml) arch_config_string = yaml.dump(config_yaml)
arch_llm_config_string = yaml.dump(config_yaml) arch_llm_config_string = yaml.dump(config_yaml)
prompt_gateway_listener = config_yaml.get("listeners", {}).get("prompt_gateway", {}) prompt_gateway_listener = config_yaml.get("listeners", {}).get(
"ingress_traffic", {}
)
if prompt_gateway_listener.get("port") == None: if prompt_gateway_listener.get("port") == None:
prompt_gateway_listener["port"] = 10000 # default port for prompt gateway prompt_gateway_listener["port"] = 10000 # default port for prompt gateway
if prompt_gateway_listener.get("address") == None: if prompt_gateway_listener.get("address") == None:
@ -112,7 +114,7 @@ def validate_and_render_schema():
if prompt_gateway_listener.get("timeout") == None: if prompt_gateway_listener.get("timeout") == None:
prompt_gateway_listener["timeout"] = "10s" prompt_gateway_listener["timeout"] = "10s"
llm_gateway_listener = config_yaml.get("listeners", {}).get("llm_gateway", {}) llm_gateway_listener = config_yaml.get("listeners", {}).get("egress_traffic", {})
if llm_gateway_listener.get("port") == None: if llm_gateway_listener.get("port") == None:
llm_gateway_listener["port"] = 12000 # default port for llm gateway llm_gateway_listener["port"] = 12000 # default port for llm gateway
if llm_gateway_listener.get("address") == None: if llm_gateway_listener.get("address") == None:

4
arch/tools/cli/core.py
View file

@ -143,12 +143,12 @@ def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
prompt_gateway_port = ( prompt_gateway_port = (
arch_config_dict.get("listeners", {}) arch_config_dict.get("listeners", {})
.get("prompt_gateway", {}) .get("ingress_traffic", {})
.get("port", 10000) .get("port", 10000)
) )
llm_gateway_port = ( llm_gateway_port = (
arch_config_dict.get("listeners", {}) arch_config_dict.get("listeners", {})
.get("llm_gateway", {}) .get("egress_traffic", {})
.get("port", 12000) .get("port", 12000)
) )

2
demos/samples_java/weather_forcecast_service/arch_config.yaml
View file

@ -1,6 +1,6 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
demos/samples_python/currency_exchange/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
demos/samples_python/human_resources_agent/arch_config.yaml
View file

@ -1,6 +1,6 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
demos/samples_python/multi_turn_rag_agent/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
demos/samples_python/network_switch_operator_agent/arch_config.yaml
View file

@ -1,6 +1,6 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

3
demos/samples_python/stock_quote/arch_config.yaml
View file

@ -1,11 +1,12 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai
timeout: 30s timeout: 30s
llm_providers: llm_providers:
- name: gpt-4o - name: gpt-4o
access_key: $OPENAI_API_KEY access_key: $OPENAI_API_KEY

2
demos/samples_python/weather_forecast/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: "0.1-beta" version: "0.1-beta"
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

4
demos/use_cases/llm_routing/arch_config.yaml
View file

@ -1,9 +1,9 @@
version: "0.1-beta" version: "0.1-beta"
listeners: listeners:
prompt_gateway: egress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 12000
message_format: openai message_format: openai
timeout: 30s timeout: 30s

2
demos/use_cases/ollama/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
demos/use_cases/spotify_bearer_auth/arch_config.yaml
View file

@ -1,6 +1,6 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

2
docs/source/concepts/includes/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

6
docs/source/get_started/quickstart.rst
View file

@ -43,7 +43,7 @@ Create ``arch_config.yaml`` file with the following content:
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai
@ -146,9 +146,9 @@ Create ``arch_config.yaml`` file with the following content:
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: egress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 12000
message_format: openai message_format: openai
timeout: 30s timeout: 30s

2
docs/source/guides/includes/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai

6
docs/source/resources/includes/arch_config_full_reference.yaml
View file

@ -1,14 +1,16 @@
version: v0.1 version: v0.1
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai
timeout: 5s timeout: 5s
llm_gateway: egress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 12000 port: 12000
message_format: openai
timeout: 5s
# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem. # Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
endpoints: endpoints:

2
tests/archgw/arch_config.yaml
View file

@ -1,7 +1,7 @@
version: "0.1-beta" version: "0.1-beta"
listeners: listeners:
prompt_gateway: ingress_traffic:
address: 0.0.0.0 address: 0.0.0.0
port: 10000 port: 10000
message_format: openai message_format: openai