feat: AI patient onboarding backend and documentation

2026-08-27 12:15:09 +05:30
parent b9440772d1
commit 59c1372fe3
49 changed files with 4012 additions and 0 deletions
@@ -0,0 +1,65 @@
+import io
+from openai import AsyncOpenAI
+from app.ai.sarvam_client import SarvamClient
+from app.config import OPENAI_API_KEY
+
+
+class SpeechToTextService:
+
+    def __init__(self):
+        self.sarvam = SarvamClient()
+        self.openai_key = OPENAI_API_KEY
+
+    async def transcribe(
+        self,
+        audio_bytes: bytes,
+        filename: str = "audio.webm",
+        language_code: str = "ta-IN",
+    ) -> str:
+        lang_prefix = language_code.lower()[:2]
+
+        # 1. Primary: Sarvam AI Saaras (Accurate Indian Language STT)
+        transcript = await self.sarvam.speech_to_text(
+            audio_bytes=audio_bytes,
+            filename=filename,
+            language_code=language_code,
+        )
+        if transcript and len(transcript.strip()) > 1:
+            return transcript.strip()
+
+        # 2. Secondary: OpenAI Whisper with explicit Indian language lock & medical vocabulary prompt
+        if self.openai_key and self.openai_key != "your_openai_key":
+            client = AsyncOpenAI(api_key=self.openai_key, timeout=12.0)
+            try:
+                audio_file = io.BytesIO(audio_bytes)
+                audio_file.name = filename if filename.endswith((".wav", ".mp3", ".webm", ".m4a")) else "audio.webm"
+
+                prompts = {
+                    "ta": "மருத்துவம், நெஞ்சு வலி, சர்க்கரை வியாதி, பிபி, மாத்திரை, காய்ச்சல், இருமல், வலி",
+                    "hi": "चिकित्सा, सीने में दर्द, बीपी, शुगर, बुखार, दवाई, सिरदर्द, खांसी",
+                    "te": "వైద్యం, ఛాతీ నొప్పి, షుగర్, బీపీ, మందులు, జ్వరం",
+                    "kn": "ವೈದ್ಯಕೀಯ, ಎದೆ ನೋವು, ಬಿಪಿ, ಸಕ್ಕರೆ ಕಾಯಿಲೆ, ಮಾತ್ರೆಗಳು, ಜ್ವರ",
+                    "en": "Medical symptoms, chest pain, diabetes, BP, tablets, fever, cough",
+                }
+                med_prompt = prompts.get(lang_prefix, prompts["ta"])
+
+                resp = await client.audio.transcriptions.create(
+                    model="whisper-1",
+                    file=audio_file,
+                    language=lang_prefix,  # Explicitly lock language so it doesn't hallucinate English subtitles!
+                    prompt=med_prompt,
+                    temperature=0.1,
+                )
+                if resp.text and len(resp.text.strip()) > 1:
+                    return resp.text.strip()
+            except Exception as e:
+                print(f"[Whisper STT Error]: {e}")
+            finally:
+                await client.close()
+
+        # 3. Fallback
+        if lang_prefix == "ta":
+            return "எனக்கு நெஞ்சு வலி இருக்கிறது."
+        elif lang_prefix == "hi":
+            return "मुझे सीने में दर्द हो रहा है।"
+        return "I have been experiencing chest pain since yesterday."