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

Chad's big patient intake PR (#40)

Browse Source 
* at least it runs, kind of

* wip

* wip with user response aggregator

* frame and pipeline docstrings

* Getting started on docstrings

* finish docstrings for aggregators

* patient intake is working!

* cleanup

* cleanup

---------

Co-authored-by: Moishe Lettvin <moishel@gmail.com>
This commit is contained in:
chadbailey59
2024-03-07 17:41:32 -06:00
committed by GitHub
parent 2bcb4966d3
commit 3c5f4800d4
12 changed files with 481 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/dailyai/services/azure_ai_services.py
View File

@@ -2,6 +2,7 @@ import aiohttp
import asyncio
import io
import json
import time
from openai import AsyncAzureOpenAI
import os
@@ -48,8 +49,8 @@ class AzureTTSService(TTSService):
class AzureLLMService(LLMService):
def __init__(self, *, api_key, endpoint, api_version="2023-12-01-preview", model):
super().__init__()
def __init__(self, *, api_key, endpoint, api_version="2023-12-01-preview", model, tools=None, messages=None):
super().__init__(tools=tools, messages=messages)
self._model: str = model
self._client = AsyncAzureOpenAI(
@@ -58,16 +59,22 @@ class AzureLLMService(LLMService):
api_version=api_version,
)
async def run_llm_async(self, messages) -> AsyncGenerator[str, None]:
async def run_llm_async(self, messages, tool_choice=None) -> AsyncGenerator[str, None]:
messages_for_log = json.dumps(messages)
self.logger.debug(f"Generating chat via azure: {messages_for_log}")
chunks = await self._client.chat.completions.create(model=self._model, stream=True, messages=messages)
if self._tools:
tools = self._tools
else:
tools = None
start_time = time.time()
chunks = await self._client.chat.completions.create(model=self._model, stream=True, messages=messages, tools=tools, tool_choice=tool_choice)
self.logger.info(f"=== Azure OpenAI LLM TTFB: {time.time() - start_time}")
async for chunk in chunks:
if len(chunk.choices) == 0:
continue
if chunk.choices[0].delta.content:
if chunk.choices[0].delta.tool_calls:
yield chunk.choices[0].delta.tool_calls[0]
elif chunk.choices[0].delta.content:
yield chunk.choices[0].delta.content
async def run_llm(self, messages) -> str | None: