Skip to content

docs: orchestration fallback added as an example #151

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
yamaceay wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: orchestration fallback added as an example #151

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions packages/gen/docs/gen_ai_hub/examples/orchestration-service2.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,59 @@
"print(result.final_result.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "077b1f69",
"metadata": {},
"source": [
"(orchestration_fallback)=\n",
"### Using Fallback Configurations\n",
"\n",
"You can provide multiple `ModuleConfig` objects to `OrchestrationConfig` instead of a single one.\n",
"The configurations are tried in order: if a call with one configuration fails, the next one is used as fallback.\n",
"\n",
"This works for both regular and streaming calls.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "827c4812",
"metadata": {},
"outputs": [],
"source": [
"from gen_ai_hub.orchestration_v2 import (SystemMessage, UserMessage, Template, PromptTemplatingModuleConfig,\n",
" LLMModelDetails, ModuleConfig, OrchestrationConfig, OrchestrationService)\n",
"\n",
"working_config = ModuleConfig(\n",
" prompt_templating=PromptTemplatingModuleConfig(\n",
" prompt=Template(template=[UserMessage(content=\"What is the longest river on planet earth?\")]),\n",
" model=LLMModelDetails(name=\"gpt-4o-mini\"),\n",
" )\n",
")\n",
"\n",
"second_working_config = ModuleConfig(\n",
" prompt_templating=PromptTemplatingModuleConfig(\n",
" prompt=Template(template=[UserMessage(content=\"What is the longest river on planet earth?\")]),\n",
" model=LLMModelDetails(name=\"gpt-4o\"),\n",
" )\n",
")\n",
"\n",
"broken_config = ModuleConfig(\n",
" prompt_templating=PromptTemplatingModuleConfig(\n",
" prompt=Template(template=[UserMessage(content=\"What is the longest river on planet earth?\")]),\n",
" model=LLMModelDetails(name=\"dummy-model\"),\n",
" )\n",
")\n",
"\n",
"# broken_config is tried first and will fail, so working_config is used as fallback\n",
"config = OrchestrationConfig(modules=[broken_config, working_config, second_working_config])\n",
"\n",
"service = OrchestrationService(config=config)\n",
"result = service.run()\n",
"print(result.final_result.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "1bd44dc91b57793d",
Expand Down
Loading