refactor: update Dockerfile to use poetry for mediapipe installation; restructure Twilio bot classes to initialize request overrides in constructors; change return type of call method in inbuilt_tools.py; remove unused run_v2 method in VideoBots.py; fix variable naming in create_twilio_sip_trunk.py; disable translation tests

Author: devxpy

Dockerfile

@@ -52,7 +52,7 @@ RUN poetry run playwright install-deps && poetry run playwright install chromium
 ARG RUN_LIVEKIT=${RUN_LIVEKIT}
 ENV RUN_LIVEKIT=${RUN_LIVEKIT}
 RUN if [ -z "$RUN_LIVEKIT" ]; then \
-        pip install --no-cache-dir mediapipe; \
+        poetry run pip install --no-cache-dir mediapipe; \
     fi
 
 # copy the code into the container

daras_ai_v2/twilio_bot.py

@@ -18,11 +18,11 @@
 class TwilioSMS(BotInterface):
     platform = Platform.TWILIO
 
-    request_overrides = dict(
-        variables=dict(platform_medium="SMS"),
-    )
-
     def __init__(self, data: dict):
+        self.request_overrides = dict(
+            variables=dict(platform_medium="SMS"),
+        )
+
         account_sid = data["AccountSid"][0]
         if account_sid == settings.TWILIO_ACCOUNT_SID:
             account_sid = ""
@@ -117,10 +117,6 @@ def send_sms_message(
 class TwilioVoice(BotInterface):
     platform = Platform.TWILIO
 
-    request_overrides = dict(
-        variables=dict(platform_medium="VOICE"),
-    )
-
     @classmethod
     def from_webhook_data(cls, data: dict):
         ## data samples:
@@ -182,6 +178,9 @@ def __init__(
         text: str = None,
         audio_url: str = None,
     ):
+        self.request_overrides = dict(
+            variables=dict(platform_medium="VOICE"),
+        )
         self.convo = convo
 
         self.bot_id = convo.bot_integration.twilio_phone_number.as_e164

functions/inbuilt_tools.py

@@ -75,7 +75,7 @@ def __init__(self, state: dict):
             required=["queries"],
         )
 
-    def call(self, queries: list[str]) -> str:
+    def call(self, queries: list[str]) -> dict[str, list[str]]:
         from daras_ai_v2.vector_search import get_top_k_references, DocSearchRequest
         from daras_ai_v2.language_model_openai_realtime import yield_from
 

glossary_resources/tests.py

@@ -1,4 +1,5 @@
 import pytest
+from decouple import config
 
 from daras_ai.image_input import gcs_blob_for
 from daras_ai_v2 import settings
@@ -74,7 +75,10 @@ def glossary_url():
         GlossaryResource.objects.all().delete()
 
 
-@pytest.mark.skipif(not settings.GS_BUCKET_NAME, reason="No GCS bucket")
+@pytest.mark.skipif(
+    not settings.GS_BUCKET_NAME or not config("RUN_GOOGLE_TRANSLATE_TESTS", None),
+    reason="No bucket name or run google translate tests",
+)
 def test_google_translate_glossary(transactional_db, glossary_url, threadpool_subtest):
     for text, expected, expected_with_glossary in TRANSLATION_TESTS_GLOSSARY:
         threadpool_subtest(

recipes/TextToSpeech.py

@@ -74,18 +74,6 @@ class TextToSpeechPage(BasePage):
         "compare-text-to-speech-engines",
     ]
 
-    sane_defaults = {
-        "tts_provider": TextToSpeechProviders.GOOGLE_TTS.value,
-        "google_voice_name": "en-IN-Wavenet-A",
-        "google_pitch": 0.0,
-        "google_speaking_rate": 1.0,
-        "uberduck_voice_name": "Aiden Botha",
-        "uberduck_speaking_rate": 1.0,
-        "elevenlabs_model": "eleven_multilingual_v2",
-        "elevenlabs_stability": 0.5,
-        "elevenlabs_similarity_boost": 0.75,
-    }
-
     class RequestModelBase(BasePage.RequestModel):
         text_prompt: str
 

recipes/VideoBots.py

@@ -1573,58 +1573,6 @@ def additional_notes(self):
 
         return notes
 
-    def run_v2(
-        self,
-        request: "VideoBotsPage.RequestModel",
-        response: "VideoBotsPage.ResponseModel",
-    ) -> typing.Iterator[str | None]:
-        if request.tts_provider == TextToSpeechProviders.ELEVEN_LABS.name and not (
-            self.is_current_user_paying() or self.is_current_user_admin()
-        ):
-            raise UserError(
-                """
-                Please purchase Gooey.AI credits to use ElevenLabs voices <a href="/account">here</a>.
-                """
-            )
-
-        llm_model = LargeLanguageModels[request.selected_model]
-        user_input = (request.input_prompt or "").strip()
-        if not (
-            user_input
-            or request.input_audio
-            or request.input_images
-            or request.input_documents
-        ):
-            return
-
-        asr_msg, user_input = yield from self.asr_step(
-            model=llm_model, request=request, response=response, user_input=user_input
-        )
-
-        ocr_texts = yield from self.document_understanding_step(request=request)
-
-        request.translation_model = (
-            request.translation_model or DEFAULT_TRANSLATION_MODEL
-        )
-        user_input = yield from self.input_translation_step(
-            request=request, user_input=user_input, ocr_texts=ocr_texts
-        )
-
-        yield from self.build_final_prompt(
-            request=request, response=response, user_input=user_input, model=llm_model
-        )
-
-        yield from self.llm_loop(
-            request=request,
-            response=response,
-            model=llm_model,
-            asr_msg=asr_msg,
-        )
-
-        yield from self.tts_step(model=llm_model, request=request, response=response)
-
-        yield from self.lipsync_step(request, response)
-
     def render_header_extra(self):
         if self.tab == RecipeTabs.run or self.tab == RecipeTabs.preview:
             render_demo_buttons_header(self.current_pr)

scripts/create_twilio_sip_trunk.py

@@ -114,7 +114,7 @@ def get_or_create_origination_url(
     priority: int = 1,
     weight: int = 1,
     enabled: bool = True,
-) -> str:
+):
     existing = client.trunking.v1.trunks(trunk_sid).origination_urls.list()
     for ou in existing:
         if ou.sip_url != sip_url:
@@ -136,11 +136,11 @@ def get_or_create_credential_list(
     list_friendly_name: str,
 ):
     try:
-        cl = client.sip.credential_lists.create(friendly_name=list_friendly_name)
+        clists = client.sip.credential_lists.create(friendly_name=list_friendly_name)
     except TwilioException as exc:
         if exc.code == 21240:
-            cl = client.sip.credential_lists.list()
-            for cl in cl:
+            clists = client.sip.credential_lists.list()
+            for cl in clists:
                 if cl.friendly_name == list_friendly_name:
                     return cl
         raise

tests/test_translation.py

@@ -1,3 +1,6 @@
+import pytest
+from decouple import config
+
 from conftest import flaky
 from daras_ai_v2.asr import run_google_translate
 
@@ -47,6 +50,10 @@
 ]
 
 
+@pytest.mark.skipif(
+    not config("RUN_GOOGLE_TRANSLATE_TESTS", None),
+    reason="No run google translate tests",
+)
 def test_google_translate(threadpool_subtest):
     for lang, text, expected in TRANSLATION_TESTS:
         threadpool_subtest(google_translate_check, text, expected, source_language=lang)