File size: 7,339 Bytes
59df45a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
"""LangGraph Agent"""
import os
from dotenv import load_dotenv
from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition
from langgraph.prebuilt import ToolNode
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
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

from langchain.tools import Tool


load_dotenv()

def multiply(a: int, b: int) -> int:
    return a * b

multiply_tool = Tool(
    name="multiply",
    func=multiply,
    description="Multiply two numbers. Args (a: first int, b: second int)"
)

def add(a: int, b: int) -> int:
    return a + b

add_tool = Tool(
    name="add",
    func=add,
    description="Add two numbers. Args (a: first int, b: second int)"
)

def substract(a: int, b: int) -> int:
    return a - b

substract_tool = Tool(
    name="substract",
    func=substract,
    description="Substract two numbers. Args (a: first int, b: second int)"
)

def divide(a: int, b: int) -> int:
    if b == 0:
        raise ValueError("Cannot divide by zero.")
    return a / b

divide_tool = Tool(
    name="divide",
    func=divide,
    description="Divide two numbers. Args (a: first int, b: second int)"
)

def modulus(a: int, b: int) -> int:
    return a % b
    
modulus_tool = Tool(
    name="modulus",
    func=modulus,
    description="Modulus two numbers. Args (a: first int, b: second int)"
)

def wiki_search(query: str) -> str:
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return {"wiki_results": formatted_search_docs}

wiki_search_tool = Tool(
    name="wiki_search",
    func=wiki_search,
    description="Search Wikipedia for a query and return maximum 2 results. Args (query: the search query)"
)

def web_search(query: str) -> str:
    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return {"web_results": formatted_search_docs}
    
web_search_tool = Tool(
    name="web_search",
    func=web_search,
    description="Search Tavily for a query and return maximum 3 results. Args (query: the search query)"
)

def arvix_search(query: str) -> str:
    """Search Arxiv for a query and return maximum 3 result.
    
    Args:
        query: The search query."""
    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
            for doc in search_docs
        ])
    return {"arvix_results": formatted_search_docs}

arvix_search_tool = Tool(
    name="arvix_search",
    func=arvix_search,
    description="Search Arxiv for a query and return maximum 3 result. Args (query: the search query)"
)


# load the system prompt from the file
with open("system_prompt.txt", "r", encoding="utf-8") as f:
    system_prompt = f.read()

# System message
sys_msg = SystemMessage(content=system_prompt)

tools = [
    multiply_tool,
    add_tool,
    substract_tool,
    divide_tool,
    modulus_tool,
    wiki_search_tool,
    web_search_tool,
    arvix_search_tool,
]

# Build graph function
def build_graph(provider: str = "google"):
    """Build the graph"""
    # Load environment variables from .env file
    if provider == "google":
        # Google Gemini
        chat = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
    elif provider == "groq":
        # Groq https://console.groq.com/docs/models
        chat = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
    elif provider == "huggingface":
        # TODO: Add huggingface endpoint
        chat = ChatHuggingFace(
            llm=HuggingFaceEndpoint(
                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
                temperature=0,
            ),
        )
    else:
        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
    # Bind tools to LLM
    chat_with_tools = chat.bind_tools(tools)

    # Node
    def assistant(state: MessagesState):
        """Assistant node"""
        return {"messages": [llm_with_tools.invoke(state["messages"])]}
    
    # def retriever(state: MessagesState):
      #  """Retriever node"""
       # similar_question = vector_store.similarity_search(state["messages"][0].content)
        #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]}

    from langchain_core.messages import AIMessage

    def retriever(state: MessagesState):
        query = state["messages"][-1].content
        similar_doc = vector_store.similarity_search(query, k=1)[0]

        content = similar_doc.page_content
        if "Final answer :" in content:
            answer = content.split("Final answer :")[-1].strip()
        else:
            answer = content.strip()

        return {"messages": [AIMessage(content=answer)]}

   # 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")

    #builder = StateGraph(MessagesState)
    #builder.add_node("retriever", retriever)

    # Retriever ist Start und Endpunkt
    #builder.set_entry_point("retriever")
    #builder.set_finish_point("retriever")

    # Compile graph
    #return builder.compile()



    builder = StateGraph(MessagesState)
    # Define nodes: these do the work
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(tools))
    # Define edges: these determine how the control flow moves
    builder.add_edge(START, "assistant")
    builder.add_conditional_edges(
        "assistant",
        # If the latest message requires a tool, route to tools
        # Otherwise, provide a direct response
        tools_condition,
    )
    builder.add_edge("tools", "assistant")

    # Compile graph
    return builder.compile()