Upload folder using huggingface_hub

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

README.md

@@ -1,12 +1,6 @@
 ---
-title: Agentic Health Model 70B
-emoji: 🐠
-colorFrom: blue
-colorTo: red
+title: Agentic_Health_Model_70B
+app_file: model_gradio.py
 sdk: gradio
 sdk_version: 5.25.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

model_gradio.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from typing import Any
+RUNPOD_POD_ID = "q39au00uendckb"
+
+client = InferenceClient(base_url=f"https://{RUNPOD_POD_ID}-8080.proxy.runpod.net/v1/chat/completions")
+
+def inference(message: str, history: list[tuple[str, str]]) -> Any:
+    partial_message = ""
+    output = client.chat.completions.create(
+        messages=[
+            {"role": "system", "content": "You are a helpful medical expert. Please answer the user's medical question as accurately as possible. Assume the user is a clinician."},
+            {"role": "user", "content": message},
+        ],
+        stream=True,
+        max_tokens=5000,
+    )
+
+    for chunk in output:
+        partial_message += chunk.choices[0].delta.content
+        yield partial_message
+
+gr.ChatInterface(
+    inference,
+    type="messages",
+    description="Chat UI for Agentic Health Model 70B",
+    title="meda",
+    examples=["What are common treatments for sepsis?", "What are the symptoms of a heart attack?", "What is the best way to treat a cold?", "What is the best way to treat a headache?"],
+).queue().launch(share=True)

runpod_model_inference.py

@@ -0,0 +1,35 @@
+# import json
+from typing import Any
+import requests
+
+# Ref: https://medium.com/@shrinath.suresh/deploying-tgi-in-runpod-a84738263e2c
+
+RUNPOD_POD_ID = "q39au00uendckb"
+
+def predict(query: str) -> Any:
+    url = f"https://{RUNPOD_POD_ID}-8080.proxy.runpod.net/v1/chat/completions"
+    headers = {
+        'Content-Type': 'application/json'
+    }
+    data = {
+        "model": "tgi",
+        "messages": [
+            {
+                "role": "system",
+                "content": "You are a helpful medical expert. Answer the user's medical question as accurately as possible."
+            },
+            {
+                "role": "user",
+                "content": query
+            }
+        ],
+        "stream": False,
+        "max_tokens": 5000,
+    }
+
+    response = requests.post(url, headers=headers, json=data)
+    result = response.json()['choices'][0]['message']['content']
+    return result
+
+response = predict("What are common treatments for sepsis?")
+print(response)