wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Anthropic tool use core Pipecat pieces refactored (#369)

Browse Source 
* processors(rtvi): rtvi 0.1 message protocol

* added a single function call handler

* wip - function calling

* fixup

* fixup

* fixup

* processors(rtvi): no need for configure_on_start()

* processors(rtvi): add new option values if they haven't been set yet

* Add the model name to the LLM usage metrics

* wip - anthropic tool calling

* still wip - anthropic tool use and vision

* anthropic tools and vision working

* anthropic tool calling and vision

* Cartesia error handling

* Anthropic tool use core Pipecat pieces refactored as per plan

* aleix has good ideas

* Usage metrics for Anthropic LLMs

* fix function call result state not getting cleared bug

* Pass **kwargs through from AnthropicLLMService constructor

* about to tinker with anthropic

* added openai function calling

* openai function calling

* fixup

---------

Co-authored-by: Aleix Conchillo Flaqué <aleix@daily.co>
Co-authored-by: Chad Bailey <chadbailey@gmail.com>
Co-authored-by: mattie ruth backman <mattieruth@gmail.com>
Co-authored-by: chadbailey59 <chadbailey59@users.noreply.github.com>
This commit is contained in:
Kwindla Hultman Kramer
2024-08-13 11:01:24 -07:00
committed by GitHub
parent a42d0c9907
commit 29ca1b7855
13 changed files with 1009 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/foundational/14-function-calling.py
View File

@@ -36,11 +36,11 @@ logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def start_fetch_weather(llm):
await llm.push_frame(TextFrame("Let me think."))
async def start_fetch_weather(llm, function_name):
await llm.push_frame(TextFrame("Let me check on that."))
async def fetch_weather_from_api(llm, args):
async def fetch_weather_from_api(llm, function_name, args):
return {"conditions": "nice", "temperature": "75"}
@@ -69,8 +69,11 @@ async def main():
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
# Register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function(
"get_current_weather",
#"get_current_weather",
None,
fetch_weather_from_api,
start_callback=start_fetch_weather)