apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-23 15:38:07 +02:00
Code Issues Projects Releases Packages Wiki Activity

add retry

Browse source
This commit is contained in:
Adil Hafeez 2025-09-17 17:53:19 -07:00
parent 71658ddbd9
commit a3f93de85d
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
7 changed files with 29 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -44,7 +44,7 @@ listeners:
- access_key: $OPENAI_API_KEY
model: openai/gpt-4o-mini
address: 0.0.0.0
port: 9000
port: 12000
tracing:
random_sampling: 100

9
demos/use_cases/rag_agent/docker-compose.yaml
View file

@ -6,3 +6,12 @@ services:
- "16686:16686"
- "4317:4317"
- "4318:4318"
open-web-ui:
image: ghcr.io/open-webui/open-webui:main
restart: always
ports:
- "8080:8080"
environment:
- DEFAULT_MODEL=gpt-4o-mini
- ENABLE_OPENAI_API=true
- OPENAI_API_BASE_URL=http://host.docker.internal:8001/v1

4
demos/use_cases/rag_agent/src/rag_agent/content_builder_agent.py
View file

@ -18,7 +18,7 @@ logger = logging.getLogger(__name__)
# Configuration for archgw LLM gateway
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:9000/v1")
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:12000/v1")
RAG_MODEL = "gpt-4o-mini"
# Initialize OpenAI client for archgw
@ -91,7 +91,7 @@ async def find_relevant_passages(
logger.info(f"Calling archgw to find relevant passages for query: '{query}'")
# Prepare extra headers if traceparent is provided
extra_headers = {}
extra_headers = {"x-envoy-max-retries": "3"}
if traceparent:
extra_headers["traceparent"] = traceparent

4
demos/use_cases/rag_agent/src/rag_agent/query_rewriter_agent.py
View file

@ -16,7 +16,7 @@ logger = logging.getLogger(__name__)
# Configuration for archgw LLM gateway
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:9000/v1")
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:12000/v1")
QUERY_REWRITE_MODEL = "gpt-4o-mini"
# Initialize OpenAI client for archgw
@ -50,7 +50,7 @@ async def rewrite_query_with_archgw(
try:
# Call archgw using OpenAI client
extra_headers = {}
extra_headers = {"x-envoy-max-retries": "3"}
if traceparent_header:
extra_headers["traceparent"] = traceparent_header
logger.info(f"Calling archgw at {LLM_GATEWAY_ENDPOINT} to rewrite query")

6
demos/use_cases/rag_agent/src/rag_agent/response_generator_agent.py
View file

@ -20,7 +20,7 @@ logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Configuration for archgw LLM gateway
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:9000/v1")
LLM_GATEWAY_ENDPOINT = os.getenv("LLM_GATEWAY_ENDPOINT", "http://localhost:12000/v1")
RESPONSE_MODEL = "gpt-4o"
# System prompt for response generation
@ -94,7 +94,7 @@ async def stream_chat_completions(
)
# Prepare extra headers if traceparent is provided
extra_headers = {}
extra_headers = {"x-envoy-max-retries": "3"}
if traceparent_header:
extra_headers["traceparent"] = traceparent_header
@ -191,7 +191,7 @@ async def non_streaming_chat_completions(
logger.info(f"Calling archgw at {LLM_GATEWAY_ENDPOINT} to generate response")
# Prepare extra headers if traceparent is provided
extra_headers = {}
extra_headers = {"x-envoy-max-retries": "3"}
if traceparent_header:
extra_headers["traceparent"] = traceparent_header