t

app.py

@@ -10,7 +10,41 @@ _ = load_dotenv(find_dotenv())
 
 databricks_token  = os.getenv('DATABRICKS_TOKEN')
 model_uri  = "https://dbc-eb788f31-6c73.cloud.databricks.com/serving-endpoints/Mpt-7b-tester/invocations"
-n_shot_learning = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+def extract_json(gen_text, n_shot_learning=0):
+    start_index = gen_text.index("### Response:\n{") + 14
+    if(n_shot_learning > 0) :
+        for i in range(0, n_shot_learning):
+            gen_text = gen_text[start_index:]
+            start_index = gen_text.index("### Response:\n{") + 14
+    end_index = gen_text.index("}\n\n### ") + 1
+    return gen_text[start_index:end_index]
+
+def score_model(model_uri, databricks_token, prompt):
+  dataset=pd.DataFrame({
+            "prompt":[prompt],
+            "temperature": [0.5],
+            "max_tokens": [1000]})
+  headers = {
+    "Authorization": f"Bearer {databricks_token}",
+    "Content-Type": "application/json",
+  }
+  ds_dict = {'dataframe_split': dataset.to_dict(orient='split')} if isinstance(dataset, pd.DataFrame) else create_tf_serving_json(dataset)
+  data_json = json.dumps(ds_dict, allow_nan=True)
+  print("***ds_dict: ")
+  print(ds_dict)
+  print("***data_json: ")
+  print(data_json)
+  response = requests.request(method='POST', headers=headers, url=model_uri, data=data_json)
+  if response.status_code != 200:
+      raise Exception(f"Request failed with status {response.status_code}, {response.text}")
+  return response.json()
+
+def get_completion(prompt):
+    return score_model(model_uri, databricks_token, prompt)
+
+def greet(input):
+	n_shot_learning = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
 ### Instruction:
 You are demanding customer
@@ -57,45 +91,7 @@ I am building an online community to help people to find dates.
 {{"solution": "FindDates.com", "problem": "finding a date", "features": "online community to help people find dates", "target_customer": "people looking for a date", "fg_will_use": "True", "reason_to_use": "I am looking for an online community to help people find dates. FindDates.com meets my needs and I would use it to find my next great date.","fg_will_pay": "True", "reason_to_pay": "I would not pay for it as I am looking for an online community to help people find dates. But for products related to dating, paying for it would be a no-brainer.","fg_will_invest": "False", "reason_to_invest": "There are many online dating platforms already.","score": "40"}}
 """
 
-def extract_json(gen_text, n_shot_learning=0):
-    start_index = gen_text.index("### Response:\n{") + 14
-    if(n_shot_learning > 0) :
-        for i in range(0, n_shot_learning):
-            gen_text = gen_text[start_index:]
-            start_index = gen_text.index("### Response:\n{") + 14
-    end_index = gen_text.index("}\n\n### ") + 1
-    return gen_text[start_index:end_index]
-
-def score_model(model_uri, databricks_token, prompt):
-  dataset=pd.DataFrame({
-            "prompt":[prompt],
-            "temperature": [0.5],
-            "max_tokens": [1000]})
-  headers = {
-    "Authorization": f"Bearer {databricks_token}",
-    "Content-Type": "application/json",
-  }
-  ds_dict = {'dataframe_split': dataset.to_dict(orient='split')} if isinstance(dataset, pd.DataFrame) else create_tf_serving_json(dataset)
-  data_json = json.dumps(ds_dict, allow_nan=True)
-  print("***ds_dict: ")
-  print(ds_dict)
-  print("***data_json: ")
-  print(data_json)
-  response = requests.request(method='POST', headers=headers, url=model_uri, data=data_json)
-  if response.status_code != 200:
-      raise Exception(f"Request failed with status {response.status_code}, {response.text}")
-  return response.json()
-
-def get_completion(prompt):
-    return score_model(model_uri, databricks_token, prompt)
-#def get_completion(prompt):
-
-def greet(company, solution, target_customer, problem, features, target_audience_persona="the target customer"):
-	customer_persona = target_audience_persona
-	pitch = f"""My company, {company} is developing {solution} to help {target_customer} {problem} with {features}"""
-	input = pitch
-
-	sys_msg=f"You are {customer_persona}."
+	sys_msg="You are demanding customer."
 
 	instruction = """Determine the product or solution, the problem being solved, features, target customer that are being discussed in the \
 following user prompt. State if you would use this product and elaborate on why. Also state if you would pay for it and elaborate on why.\
@@ -123,6 +119,11 @@ Give a score for the product. Format your response as a JSON object with \
 	response = get_completion(total_prompt)
 	gen_text = response["predictions"][0]["generated_text"]
 	return json.dumps(extract_json(gen_text, 3))
+	#return json.dumps(response)
+
+#iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+#iface.launch()
 
-iface = gr.Interface(fn=greet, inputs=[gr.Textbox(label="Company"), gr.Textbox(label="Solution"), gr.Textbox(label="Customer"), gr.Textbox(label="Problem"), gr.Textbox(label="Feature"), gr.Textbox(label="Target Audience persona", lines=3)], outputs="json")
+#iface = gr.Interface(fn=greet, inputs=[gr.Textbox(label="Text to find entities", lines=2)], outputs=[gr.HighlightedText(label="Text with entities")], title="NER with dslim/bert-base-NER", description="Find entities using the `dslim/bert-base-NER` model under the hood!", allow_flagging="never", examples=["My name is Andrew and I live in California", "My name is Poli and work at HuggingFace"])
+iface = gr.Interface(fn=greet, inputs=[gr.Textbox(label="Elevator pitch", lines=3)], outputs="json")
 iface.launch()