File size: 4,134 Bytes
dc66050 3674844 ee14926 dc66050 ee14926 dc66050 ee14926 dc66050 ee14926 2d1e4f3 ee14926 2d1e4f3 ee14926 2d1e4f3 ee14926 2d1e4f3 ee14926 2d1e4f3 ee14926 2d1e4f3 ee14926 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
import gradio as gr
from huggingface_hub import InferenceClient
import os
from smolagents import tool, CodeAgent, HfApiModel, GradioUI # type: ignore
# testing teste
"""
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", token=os.getenv("my_first_agents_hf_tokens")
)
def sql_engine(query: str) -> str:
"""
Allows you to perform SQL queries on the table. Returns a string representation of the result.
The table is named 'receipts'. Its description is as follows:
Columns:
- receipt_id: INTEGER
- customer_name: VARCHAR(16)
- price: FLOAT
- tip: FLOAT
Args:
query: The query to perform. This should be correct SQL.
"""
output = ""
with engine.connect() as con:
rows = con.execute(text(query))
for row in rows:
output += "\n" + str(row)
return output
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
# agent.run("Can you give me the name of the client who got the most expensive receipt?")
for message in agent.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
"""
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)",
),
],
)
if __name__ == "__main__":
agent = CodeAgent(
tools=[sql_engine],
model=HfApiModel(
model_id="meta-llama/Meta-Llama-3.1-8B-Instruct",
token=os.getenv("my_first_agents_hf_tokens"),
),
)
from sqlalchemy import (
create_engine,
MetaData,
Table,
Column,
String,
Integer,
Float,
insert,
inspect,
text,
)
engine = create_engine("sqlite:///:memory:")
metadata_obj = MetaData()
def insert_rows_into_table(rows, table, engine=engine):
for row in rows:
stmt = insert(table).values(**row)
with engine.begin() as connection:
connection.execute(stmt)
table_name = "receipts"
receipts = Table(
table_name,
metadata_obj,
Column("receipt_id", Integer, primary_key=True),
Column("customer_name", String(16), primary_key=True),
Column("price", Float),
Column("tip", Float),
)
metadata_obj.create_all(engine)
rows = [
{"receipt_id": 1, "customer_name": "Alan Payne", "price": 12.06, "tip": 1.20},
{"receipt_id": 2, "customer_name": "Alex Mason", "price": 23.86, "tip": 0.24},
{
"receipt_id": 3,
"customer_name": "Woodrow Wilson",
"price": 53.43,
"tip": 5.43,
},
{
"receipt_id": 4,
"customer_name": "Margaret James",
"price": 21.11,
"tip": 1.00,
},
]
insert_rows_into_table(rows, receipts)
GradioUI(agent).launch()
|