Scripts-deploy-VMs-models

crew2.py

@@ -1,7 +1,7 @@
 import concurrent.futures
 import sys
 import uuid
-from contextlib import contextmanager
+from contextlib import contextmanager, nullcontext
 from dotenv import load_dotenv
 
 from crewai import Agent, Crew, LLM, Process, Task
@@ -14,15 +14,19 @@ load_dotenv()
 try:
     from openinference.instrumentation import using_session as _using_session
 except ImportError:
+
     @contextmanager
     def _using_session(session_id):  # noqa: F811
         yield
 
+
 try:
     from openinference.semconv.trace import SpanAttributes
 except ImportError:
+
     class _SpanAttributes:
         SESSION_ID = "session_id"
+
     SpanAttributes = _SpanAttributes()  # type: ignore
 
 # ------ Phoenix / OpenTelemetry tracing ------
@@ -46,9 +50,11 @@ try:
         endpoint="https://RCaz-phoenix-arize-observability.hf.space/v1/traces",
         headers=build_hf_headers(),
     )
+    OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
     CrewAIInstrumentor().instrument(tracer_provider=tracer_provider)
+    tracer = trace.get_tracer("crewai")
 except ImportError:
-    pass
+    tracer = None
 
 
 ###### The agentic app
@@ -232,7 +238,7 @@ Two research crews investigated it. Here are their findings:
 {result_opposite}
 
 Your job:
-Create a highly detailed visual scene description that captures the dialogue, contrast, or tension between these two perspectives. Describe the composition, colors, lighting, mood, subjects, setting, and visual metaphor in vivid detail — as if instructing an artist or image generation model.
+Create a highly detailed visual scene description that captures and merges the dialogue, contrast, or tension between these two perspectives. Describe the composition, colors, lighting, mood, subjects, setting, and visual metaphor in vivid detail — as if instructing an artist or image generation model.
 
 Output exactly in this format:
 
@@ -281,21 +287,26 @@ def generate_image(prompt: str) -> bytes:
 
     import httpx as _httpx
 
-    url = _get_flux_url()
-    resp = _httpx.post(
-        url,
-        json={"prompt": prompt, "steps": 30},
-        timeout=600,
-        follow_redirects=True,
-    )
-    resp.raise_for_status()
-    return resp.content
+    with (
+        tracer.start_as_current_span("flux.generate_image") if tracer else nullcontext()
+    ):
+        url = _get_flux_url()
+        resp = _httpx.post(
+            url,
+            json={"prompt": prompt, "steps": 30},
+            timeout=600,
+            follow_redirects=True,
+        )
+        resp.raise_for_status()
+        return resp.content
 
 
 # ------ Caption Generation (direct LLM call with image prompt context) ------
 
 
-def generate_caption(corroborate: str, opposite: str, image_prompt: str, session_id: str | None = None) -> dict:
+def generate_caption(
+    corroborate: str, opposite: str, image_prompt: str, session_id: str | None = None
+) -> dict:
     """
     Send the research + image prompt to Gemma 4 and get a 30-second
     spoken caption + voice style back.
@@ -343,15 +354,34 @@ VOICE_STYLE: <voice style description>""",
     }
 
     with _using_session(session_id):
-        resp = _httpx.post(
-            f"{_VLLM_BASE_URL}/chat/completions",
-            json=payload,
-            headers={"Authorization": "Bearer sk-dummy-key-not-needed"},
-            timeout=300,
+        _span_cm = (
+            tracer.start_as_current_span("llm.generate_caption")
+            if tracer
+            else nullcontext()
         )
-        resp.raise_for_status()
-        body = resp.json()
-        text = body["choices"][0]["message"]["content"]
+        with _span_cm as _span:
+            resp = _httpx.post(
+                f"{_VLLM_BASE_URL}/chat/completions",
+                json=payload,
+                headers={"Authorization": "Bearer sk-dummy-key-not-needed"},
+                timeout=300,
+            )
+            resp.raise_for_status()
+            body = resp.json()
+            text = body["choices"][0]["message"]["content"]
+
+            if tracer and "usage" in body:
+                usage = body["usage"]
+                _span.set_attribute(
+                    "llm.token_count.prompt", usage.get("prompt_tokens", 0)
+                )
+                _span.set_attribute(
+                    "llm.token_count.completion", usage.get("completion_tokens", 0)
+                )
+                _span.set_attribute(
+                    "llm.token_count.total", usage.get("total_tokens", 0)
+                )
+                _span.set_attribute("llm.model_name", _VLLM_SERVED_MODEL)
 
     print(f"Gemma response:\n{text}\n")
 
@@ -369,7 +399,9 @@ VOICE_STYLE: <voice style description>""",
 # ------ Voice Generation (VoxCPM on Modal) ------
 
 
-def generate_voice(voice_style: str, voice_script: str, session_id: str | None = None) -> bytes:
+def generate_voice(
+    voice_style: str, voice_script: str, session_id: str | None = None
+) -> bytes:
     """Send script to VoxCPM on Modal T4, return WAV bytes."""
     if session_id is None:
         session_id = str(uuid.uuid4())
@@ -381,15 +413,20 @@ def generate_voice(voice_style: str, voice_script: str, session_id: str | None =
     import httpx as _httpx
 
     with _using_session(session_id):
-        url = _get_vox_url()
-        resp = _httpx.post(
-            url,
-            json={"text": voice_script, "voice_style": voice_style},
-            timeout=600,
-            follow_redirects=True,
-        )
-        resp.raise_for_status()
-        return resp.content
+        with (
+            tracer.start_as_current_span("voxcpm.generate_voice")
+            if tracer
+            else nullcontext()
+        ):
+            url = _get_vox_url()
+            resp = _httpx.post(
+                url,
+                json={"text": voice_script, "voice_style": voice_style},
+                timeout=600,
+                follow_redirects=True,
+            )
+            resp.raise_for_status()
+            return resp.content
 
 
 # ------ Audio Transcription (Cohere Transcribe on Modal) ------
@@ -405,14 +442,19 @@ def transcribe_audio(audio_path: str, session_id: str | None = None) -> str:
     url = _get_transcribe_url()
 
     with _using_session(session_id):
-        with open(audio_path, "rb") as f:
-            audio_b64 = base64.b64encode(f.read()).decode()
+        with (
+            tracer.start_as_current_span("cohere.transcribe_audio")
+            if tracer
+            else nullcontext()
+        ):
+            with open(audio_path, "rb") as f:
+                audio_b64 = base64.b64encode(f.read()).decode()
 
-        resp = _httpx.post(url, json={"audio": audio_b64}, timeout=600)
-        resp.raise_for_status()
-        text = resp.json()["transcription"]
-        print(f'Transcribed: "{text}"\n')
-        return text
+            resp = _httpx.post(url, json={"audio": audio_b64}, timeout=600)
+            resp.raise_for_status()
+            text = resp.json()["transcription"]
+            print(f'Transcribed: "{text}"\n')
+            return text
 
 
 # ------ CLI Entry Point ------
@@ -461,7 +503,9 @@ if __name__ == "__main__":
         caption_result = None
         if prompt and corroborate and opposite:
             try:
-                caption_result = generate_caption(corroborate, opposite, prompt, session_id=session_id)
+                caption_result = generate_caption(
+                    corroborate, opposite, prompt, session_id=session_id
+                )
                 if caption_result["caption"]:
                     print(f"\n✓ Caption: {caption_result['caption']}")
                 if caption_result["voice_style"]:
@@ -472,10 +516,16 @@ if __name__ == "__main__":
             print("(Skipping caption generation — missing prompt or research)")
 
         # Generate voice
-        if caption_result and caption_result["voice_style"] and caption_result["caption"]:
+        if (
+            caption_result
+            and caption_result["voice_style"]
+            and caption_result["caption"]
+        ):
             try:
                 audio_bytes = generate_voice(
-                    caption_result["voice_style"], caption_result["caption"], session_id=session_id
+                    caption_result["voice_style"],
+                    caption_result["caption"],
+                    session_id=session_id,
                 )
                 filename = "crew_voice_output.wav"
                 with open(filename, "wb") as f: