Essay-Writer-AI / app.py
canon27's picture
Update app.py
e9a29a4 verified
Raw History Blame Contribute Delete
5.26 kB
import os
os.system("pip install langgraph")
from langgraph.checkpoint.sqlite import SqliteSaver
from lamini import LaminiClient
from langgraph.graph import StateGraph, END
from typing import TypedDict, Annotated, List
import operator
# from langgraph.checkpoint import SqliteSaver
from langchain_core.messages import AnyMessage, SystemMessage, HumanMessage, AIMessage, ChatMessage
from duckduckgo_search import DDGS
memory = SqliteSaver.from_conn_string(":memory:")
class AgentState(TypedDict):
task: str
plan: str
draft: str
critique: str
content: List[str]
revision_number: int
max_revisions: int
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
#model_name = "mistralai/Mistral-7B-Instruct"
#tokenizer = AutoTokenizer.from_pretrained(model_name)
#model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
lamini = LaminiClient(api_key=os.environ["LAMINI_API_KEY"])
def chat(input_text):
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
output = model.generate(**inputs, max_new_tokens=300)
return tokenizer.decode(output[0], skip_special_tokens=True)
def search_online(query):
"""使用 DuckDuckGo 进行免费搜索"""
with DDGS() as ddgs:
results = ddgs.text(query, max_results=5)
return [r["title"] + " - " + r["href"] for r in results]
PLAN_PROMPT = """You are an expert writer tasked with writing a high level outline of an essay. \
Write such an outline for the user provided topic. Give an outline of the essay along with any relevant notes \
or instructions for the sections."""
WRITER_PROMPT = """You are an essay assistant tasked with writing excellent 5-paragraph essays.\
Generate the best essay possible for the given topic while maintaining coherence and logical flow."""
REFLECTION_PROMPT = """You are a critical reviewer tasked with evaluating an essay draft.\
Provide constructive feedback on clarity, structure, and argumentation."""
RESEARCH_PLAN_PROMPT = """You are a research strategist tasked with creating a research plan.\
Generate a plan detailing the key sources, arguments, and methodologies relevant to the topic."""
RESEARCH_CRITIQUE_PROMPT = """You are an academic reviewer tasked with critiquing research plans.\
Evaluate the validity, coherence, and feasibility of the proposed research approach."""
def plan_node(state: AgentState):
messages = [
SystemMessage(content=PLAN_PROMPT),
HumanMessage(content=state['task'])
]
response = model.invoke(messages)
return {"plan": response.content}
def research_plan_node(state: AgentState):
queries = model.with_structured_output(Queries).invoke([
SystemMessage(content=RESEARCH_PLAN_PROMPT),
HumanMessage(content=state['task'])
])
content = state['content'] or []
for q in queries.queries:
response = search_online(q)
content.extend(response)
return {"content": content}
def generation_node(state: AgentState):
content = "\n\n".join(state['content'] or [])
user_message = HumanMessage(
content=f"{state['task']}\n\nHere is my plan:\n\n{state['plan']}")
messages = [
SystemMessage(content=WRITER_PROMPT.format(content=content)),
user_message
]
response = model.invoke(messages)
return {
"draft": response.content,
"revision_number": state.get("revision_number", 1) + 1
}
def reflection_node(state: AgentState):
messages = [
SystemMessage(content=REFLECTION_PROMPT),
HumanMessage(content=state['draft'])
]
response = model.invoke(messages)
return {"critique": response.content}
def research_critique_node(state: AgentState):
queries = model.with_structured_output(Queries).invoke([
SystemMessage(content=RESEARCH_CRITIQUE_PROMPT),
HumanMessage(content=state['critique'])
])
content = state['content'] or []
for q in queries.queries:
response = search_online(q)
content.extend(response)
return {"content": content}
def should_continue(state):
if state["revision_number"] > state["max_revisions"]:
return END
return "reflect"
builder = StateGraph(AgentState)
builder.add_node("planner", plan_node)
builder.add_node("generate", generation_node)
builder.add_node("reflect", reflection_node)
builder.add_node("research_plan", research_plan_node)
builder.add_node("research_critique", research_critique_node)
builder.set_entry_point("planner")
builder.add_conditional_edges(
"generate",
should_continue,
{END: END, "reflect": "reflect"}
)
builder.add_edge("planner", "research_plan")
builder.add_edge("research_plan", "generate")
builder.add_edge("reflect", "research_critique")
builder.add_edge("research_critique", "generate")
graph = builder.compile(checkpointer=memory)
thread = {"configurable": {"thread_id": "1"}}
for s in graph.stream({
'task': "what is the difference between langchain and langsmith",
"max_revisions": 2,
"revision_number": 1,
}, thread):
print(s)
import warnings
warnings.filterwarnings("ignore")
from helper import ewriter, writer_gui
MultiAgent = ewriter()
app = writer_gui(MultiAgent.graph)
app.launch()