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 comments that open ai can be swapped out
Stefan Krawczyk7801cbe85910
diff --git a/docs/getting_started/simple-example.rst b/docs/getting_started/simple-example.rstindex 5ca96e55..8350084b 100644--- a/docs/getting_started/simple-example.rst+++ b/docs/getting_started/simple-example.rst@@ -51,6 +51,7 @@ We define two actions:.. code-block:: python+ # Note: you can replace this with your favorite LLM Clientclient = openai.Client()@action(reads=[], writes=["prompt", "chat_history"])@@ -145,11 +146,11 @@ If you want to copy/paste, you can open up the following code block and add to aimport uuid- import openai+ import openai # replace with your LLM libraryfrom burr.core import action, State, ApplicationBuilder- client = openai.Client()+ client = openai.Client() # replace this if not using OpenAI@action(reads=[], writes=["prompt", "chat_history"])def human_input(state: State, prompt: str) -> State:diff --git a/examples/simple-chatbot-intro/application.py b/examples/simple-chatbot-intro/application.pyindex 418524a3..7516eac2 100644--- a/examples/simple-chatbot-intro/application.py+++ b/examples/simple-chatbot-intro/application.py@@ -1,6 +1,6 @@from typing import Tuple-import openai+import openai # replace this with your favorite LLM client libraryfrom burr.core import ApplicationBuilder, State, action, when@@ -23,7 +23,7 @@ def human_input(state: State, prompt: str) -> Tuple[dict, State]:def ai_response(state: State) -> Tuple[dict, State]:"""Queries OpenAI with the chat. You could easily use langchain, etc... to handle this,but we wanted to keep it simple to demonstrate"""- client = openai.Client()+ client = openai.Client() # replace this with your favorite LLM client librarycontent = (client.chat.completions.create(model="gpt-3.5-turbo",diff --git a/examples/simple-chatbot-intro/notebook.ipynb b/examples/simple-chatbot-intro/notebook.ipynbindex 641ef57e..5fa24b11 100644--- a/examples/simple-chatbot-intro/notebook.ipynb+++ b/examples/simple-chatbot-intro/notebook.ipynb@@ -30,7 +30,7 @@"import uuid\n","from typing import Tuple\n","\n",- "import openai\n",+ "import openai # replace with your favorite LLM client library\n","\n","from burr.core import action, State, ApplicationBuilder, when, persistence"]@@ -79,7 +79,7 @@"def ai_response(state: State) -> Tuple[dict, State]:\n"," \"\"\"Queries OpenAI with the chat. You could easily use langchain, etc... to handle this,\n"," but we wanted to keep it simple to demonstrate\"\"\"\n",- " client = openai.Client()\n",+ " client = openai.Client() # replace with your favorite LLM client library\n"," content = client.chat.completions.create(\n"," model=\"gpt-3.5-turbo\",\n"," messages=state[\"chat_history\"],\n",