Chad's big patient intake PR (#40)

* 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>

src/dailyai/services/open_ai_services.py

@@ -1,6 +1,7 @@
 import aiohttp
 from PIL import Image
 import io
+import time
 from openai import AsyncOpenAI
 
 import json
@@ -10,8 +11,8 @@ from dailyai.services.ai_services import LLMService, ImageGenService
 
 
 class OpenAILLMService(LLMService):
-    def __init__(self, *, api_key, model="gpt-4"):
-        super().__init__()
+    def __init__(self, *, api_key, model="gpt-4", tools=None, messages=None):
+        super().__init__(tools=tools, messages=messages)
         self._model = model
         self._client = AsyncOpenAI(api_key=api_key)
 
@@ -19,19 +20,26 @@ class OpenAILLMService(LLMService):
         return await self._client.chat.completions.create(
             stream=stream,
             messages=messages,
-            model=self._model
+            model=self._model,
+            tools=self._tools
         )
 
-    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 openai: {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"=== 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: