Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
Python aiburrchatbot-frameworkdagsgenerative-aigraphshacktoberfestllmopsllmsmlopspersistent-data-structurestate-machinestate-managementvisibility
Adds FastAPI example -- not fully fleshed out, but good enough for now
elijahbenizzyffb1cf52b1a2
diff --git a/burr/tracking/server/examples/chatbot.py b/burr/tracking/server/examples/chatbot.pyindex c6a6b5aa..0718f7f3 100644--- a/burr/tracking/server/examples/chatbot.py+++ b/burr/tracking/server/examples/chatbot.py@@ -11,15 +11,15 @@ from burr.core import ApplicationWe manage an application, write to it with post endpoints, and read withget/ endpoints.-This demonstrates how+This demonstrates how you can build interactive web applications with Burr!"""-# We're doing dynamic import cause this lives within examples/+# We're doing dynamic import cause this lives within examples/ (and that module has dashes)# navigate to the examples directory to read more about this!chat_application = importlib.import_module("burr.examples.multi-modal-chatbot.application") # noqa: F401-# the app is commented out as we dynamically register it+# the app is commented out as we include the router.# app = FastAPI()router = APIRouter()@@ -82,13 +82,5 @@ async def create_new_application(project_id: str, app_id: str) -> str:return app_id # just return it for now-# def register(app: FastAPI, api_prefix: str):-# app.post(-# f"{api_prefix}/{{project_id}}/{{app_id}}/response",-# response_model=List[ChatItem])(chat_response)-# app.get(f"{api_prefix}/{{project_id}}/{{app_id}}/history", response_model=List[ChatItem])(-# chat_history-# )-# app.post(f"{api_prefix}/{{project_id}}/{{app_id}}/create", response_model=str)(-# create_new_application-# )+# comment this back in fro a standalone chatbot API+# app.include_router(router, prefix="/api/v0/chatbot")diff --git a/examples/README.md b/examples/README.mdindex f865cef8..f8b23298 100644--- a/examples/README.md+++ b/examples/README.md@@ -30,3 +30,4 @@ Note we have a few more in [other-examples](other-examples/), but those do not y- [multi-modal-chatbot](multi-modal-chatbot/) - This example shows how to use Burr to create a multi-modal chatbot. This demonstrates how to use a model to delegate to other models conditionally.- [streaming-overview](streaming-overview/) - This example shows how we can use the streaming API to respond to return quicker results to the user and build a seamless experience- [tracing-and-spans](tracing-and-spans/) - This example shows how to use Burr to create a simple chatbot with additional visibility. This is a good starting point for understanding how to use Burr's tracing functionality.+- [web-server](web-server/) - This example shows how to use Burr in a web server. This is a good starting point for understanding how to use Burr for interaction.diff --git a/examples/validate_examples.py b/examples/validate_examples.pyindex f515dcd0..179ad4ca 100644--- a/examples/validate_examples.py+++ b/examples/validate_examples.py@@ -12,7 +12,14 @@ REQUIRED_FILES = ["__init__.py", # included as we want them all to be importable]-FILTERLIST = ["other-examples", "ml-training", "simulation", "multi-agent-collaboration"]+FILTERLIST = [+ "other-examples",+ # todo -- remove the following once we've fleshed them out+ "ml-training",+ "simulation",+ "multi-agent-collaboration",+ "web-server",+]def should_validate(directory: str) -> bool: