File size: 5,002 Bytes
0edbbcb
 
 
 
 
 
 
 
 
 
 
 
 
 
6b1796d
0edbbcb
 
6b1796d
0edbbcb
6b1796d
 
0edbbcb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
150
151
import os
from dotenv import load_dotenv
from typing import List, Dict, Any, Optional
import tempfile
import re
import json
import requests
from urllib.parse import urlparse
import pytesseract
from PIL import Image, ImageDraw, ImageFont, ImageEnhance, ImageFilter
import cmath
import pandas as pd
import uuid
import numpy as np
from tools.python_interpreter import CodeInterpreter

interpreter_instance = CodeInterpreter()
hf_token = os.environ["HUGGING_FACE_TOKEN"]


from tools.image import *

"""Langraph"""
from langgraph.graph import START, StateGraph, MessagesState
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
from langgraph.prebuilt import ToolNode, tools_condition
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import (
    ChatHuggingFace,
    HuggingFaceEndpoint,
    HuggingFaceEmbeddings,
)
from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client
# ------- Tools
from tools.browse import web_search, wiki_search, arxiv_search
from tools.document_process import save_and_read_file, analyze_csv_file, analyze_excel_file, extract_text_from_image, download_file_from_url
from tools.image_tools import analyze_image, generate_simple_image 
from tools.simple_math import multiply, add, subtract, divide, modulus, power, square_root
from tools.python_interpreter import execute_code_lang

load_dotenv()

with open("system_prompt.txt", "r", encoding="utf-8") as f:
    system_prompt = f.read()
print(system_prompt)

# System message
sys_msg = SystemMessage(content=system_prompt)

# build a retriever
embeddings = HuggingFaceEmbeddings(
    model_name="sentence-transformers/all-mpnet-base-v2",
)  #  dim=768
supabase: Client = create_client(
    os.environ.get("SUPABASE_URL_HUGGING_FACE"), os.environ.get("SUPABASE_SERVICE_ROLE_HUGGING_FACE")
)
vector_store = SupabaseVectorStore(
    client=supabase,
    embedding=embeddings,
    table_name="documents2",
    query_name="match_documents_2",
)
create_retriever_tool = create_retriever_tool(
    retriever=vector_store.as_retriever(),
    name="Question Search",
    description="A tool to retrieve similar questions from a vector store.",
)


tools = [
    web_search,
    wiki_search,
    arxiv_search,
    multiply,
    add,
    subtract,
    divide,
    modulus,
    power,
    square_root,
    save_and_read_file,
    download_file_from_url,
    extract_text_from_image,
    analyze_csv_file,
    analyze_excel_file,
    execute_code_lang,
    analyze_image,
    generate_simple_image,
]

def build_graph(provider: str = "groq"):
    if provider == "groq":
        # Groq https://console.groq.com/docs/models
        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
    elif provider == "huggingface":
        llm = ChatHuggingFace(
            llm=HuggingFaceEndpoint(
                repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
                task="text-generation",  # for chat‐style use “text-generation”
                max_new_tokens=1024,
                do_sample=False,
                repetition_penalty=1.03,
                temperature=0,
            ),
            verbose=True,
        )
    else:
        raise ValueError("Invalid provider. Choose 'groq' or 'huggingface'.")

    llm_with_tools = llm.bind_tools(tools)

    def assistant(state: MessagesState):
        """Assistant Node"""
        return {"messages": [llm_with_tools.invoke(state['messages'])]}

    def retriever(state: MessagesState):
        """Retriever Node"""
        similar_question = vector_store.similiarity_search(state['messages'])
        if similar_question:  
            example_msg = HumanMessage(
                content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
            )
            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
        else:
            return {"messages": [sys_msg] + state["messages"]}

    builder = StateGraph(MessagesState)
    builder.add_node("retriever", retriever)
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(tools))
    builder.add_edge(START, "retriever")
    builder.add_edge("retriever", "assistant")
    builder.add_conditional_edges("assistant", tools_condition)
    builder.add_edge("tools", "assistant")
    return builder.compile()

if __name__ == "__main__":
    question = "When was the Cyrus Cylinder created?"
    graph = build_graph(provider="groq")
    messages = [HumanMessage(content=question)]
    messages = graph.invoke({"messages": messages})
    for m in messages["messages"]:
        m.pretty_print()