panda query

app.py

@@ -1,22 +1,42 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+from groq import Groq
+from sqlalchemy import text
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta",token='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')
+
+import pandas as pd
+import pandasql
+
+# Create a sample DataFrame
+data = [
+    {"Name": "John", "Age": 25, "Gender": "male", "Votes": 100},
+    {"Name": "Mary", "Age": 30, "Gender": "female", "Votes": 200},
+    {"Name": "Bob", "Age": 28, "Gender": "male", "Votes": 150},
+    {"Name": "Alice", "Age": 24, "Gender": "female", "Votes": 120},
+]
+
+# Create a pandas dataframe from the list of dictionaries
+df = pd.DataFrame(data)
 
 
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    os.environ['GROQ_API_KEY'] = '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'
 
+    client = Groq()
+    messages = [
+        {
+            "role": "system",
+            "content": "Your task is to convert the input query into a sql statement to be used against a panda dataframe.\n\nGiven the below columns, \n\nColumn1: Age\nColumn2: Name\nColumn3: Gender\nColumn4: Votes\nColumn5: Location\nColumn6: Party\n\n and Table name as df \n and the user input text, \n\nconvert it into a proper sql statement.\n\nIn the where condition make sure you do a case insensitive comparison for text columns, and where possible use like, instead of 'equal' condition.  Also when you compare with text always use a lowercase, for example use 'female', not 'Female'. \n\nOutput format:\nIn the response give only the SQL statement starts with 'SELECT', do not add any note or any other explanations"
+        }
+    ]
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -24,38 +44,25 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
+    completion = client.chat.completions.create(
+        model="llama3-70b-8192",
+        messages=messages,
+        temperature=1,
+        max_tokens=1024,
+        top_p=1,
+        stream=False,
+        stop=None,
+    )
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    sql_command = completion.choices[0].message.content
+    result = pandasql.sqldf(sql_command, globals())
+    yield str(result)
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    respond
 )
 
 

requirements.txt

@@ -1 +1,5 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+gradio
+groq
+pandasql
+sqlalchemy==1.4.46