phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use agent.inference_api instead of passing host/port again

Browse source
This commit is contained in:
Hardik Shah 2024-09-06 12:48:08 -07:00
parent 4a70f3d2ba
commit c2b7b462e9
3 changed files with 15 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_toolchain/agentic_system/api/api.py
View file

@ -133,8 +133,6 @@ class LLMMemoryQueryGeneratorConfig(BaseModel):
type: Literal[MemoryQueryGenerator.llm.value] = MemoryQueryGenerator.llm.value
model: str
template: str
host: str = "localhost"
port: int = 5000
class CustomMemoryQueryGeneratorConfig(BaseModel):
@ -157,7 +155,7 @@ class MemoryToolDefinition(ToolDefinitionCommon):
# This config defines how a query is generated using the messages
# for memory bank retrieval.
query_generator_config: MemoryQueryGeneratorConfig = Field(
default=DefaultMemoryQueryGeneratorConfig
default=DefaultMemoryQueryGeneratorConfig()
)
max_tokens_in_context: int = 4096
max_chunks: int = 10