Upload 4 files

app_langgraph.py

@@ -0,0 +1,86 @@
+"""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_huggingface import HuggingFaceEndpoint, ChatHuggingFace, HuggingFaceEmbeddings
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.globals import set_debug
+from langchain_groq import ChatGroq
+from tools.search_tools import web_search, arvix_search, wiki_search
+from tools.math_tools import multiply, add, subtract, divide
+from supabase.client import Client, create_client
+from langchain.tools.retriever import create_retriever_tool
+from langchain_community.vectorstores import SupabaseVectorStore
+import json
+
+# set_debug(True)
+load_dotenv()
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    web_search,
+    wiki_search,
+    arvix_search
+]
+
+def build_graph():
+    hf_token = os.getenv("HF_TOKEN")
+    # llm = HuggingFaceEndpoint(
+    #     repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+    #     huggingfacehub_api_token=hf_token,
+    # )
+    
+    # chat = ChatHuggingFace(llm=llm, verbose=True)
+    # llm_with_tools = chat.bind_tools(tools)
+
+    llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    llm_with_tools = llm.bind_tools(tools)
+
+    def assistant(state: MessagesState):
+        sys_msg = "You are a helpful assistant with access to tools. Understand user requests accurately. Use your tools when needed to answer effectively. Strictly follow all user instructions and constraints." \
+        "Pay attention: your output needs to contain only the final answer without any reasoning since it will be strictly evaluated against a dataset which contains only the specific response." \
+        "Your final output needs to be just the string or integer containing the answer, not an array or technical stuff."
+        return {
+            "messages": [llm_with_tools.invoke([sys_msg] + state["messages"])],
+        }
+
+    ## The graph
+    builder = StateGraph(MessagesState)
+
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+
+    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")
+    return builder.compile()
+
+# test
+if __name__ == "__main__":
+
+    graph = build_graph()
+    with open('sample.jsonl', 'r') as jsonl_file:
+        json_list = list(jsonl_file)
+    
+    start = 10 #revisit 5, 8, 
+    end = start + 1
+    for json_str in json_list[start:end]:
+        json_data = json.loads(json_str)
+        print(f"Question::::::::: {json_data['Question']}")
+        print(f"Final answer::::: {json_data['Final answer']}")
+    
+        question = json_data['Question']
+        messages = [HumanMessage(content=question)]
+        messages = graph.invoke({"messages": messages})
+        for m in messages["messages"]:
+            m.pretty_print()

math_tools.py

@@ -0,0 +1,52 @@
+from langchain_core.tools import tool
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b

requirements.txt

@@ -1,2 +1,100 @@
-gradio
-requests
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.11
+aiosignal==1.3.2
+aiosqlite==0.21.0
+annotated-types==0.7.0
+anyio==4.9.0
+attrs==25.3.0
+banks==2.1.2
+certifi==2025.4.26
+charset-normalizer==3.4.2
+click==8.2.1
+colorama==0.4.6
+dataclasses-json==0.6.7
+Deprecated==1.2.18
+dirtyjson==1.0.8
+distro==1.9.0
+filelock==3.18.0
+filetype==1.2.0
+frozenlist==1.6.2
+fsspec==2025.3.2
+greenlet==3.2.3
+griffe==1.7.3
+h11==0.16.0
+hf-xet==1.1.0
+httpcore==1.0.9
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.31.1
+idna==3.10
+Jinja2==3.1.6
+jiter==0.10.0
+joblib==1.5.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.25
+langchain-community==0.3.25
+langchain-core==0.3.65
+langchain-huggingface==0.3.0
+langchain-openai==0.3.21
+langchain-text-splitters==0.3.8
+langgraph==0.4.8
+langgraph-checkpoint==2.0.26
+langgraph-prebuilt==0.2.2
+langgraph-sdk==0.1.70
+langsmith==0.3.45
+llama-index-core==0.12.41
+llama-index-embeddings-huggingface==0.5.4
+llama-index-llms-huggingface-api==0.5.0
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.4.4
+mypy_extensions==1.1.0
+nest-asyncio==1.6.0
+networkx==3.5
+nltk==3.9.1
+numpy==2.3.0
+openai==1.85.0
+orjson==3.10.18
+ormsgpack==1.10.0
+packaging==24.2
+pillow==11.2.1
+platformdirs==4.3.8
+propcache==0.3.1
+pydantic==2.11.5
+pydantic-settings==2.9.1
+pydantic_core==2.33.2
+Pygments==2.19.1
+python-dotenv==1.1.0
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==14.0.0
+safetensors==0.5.3
+scikit-learn==1.7.0
+scipy==1.15.3
+sentence-transformers==4.1.0
+smolagents==1.15.0
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+sympy==1.14.0
+tavily-python==0.7.5
+tenacity==9.1.2
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+torch==2.7.1
+tqdm==4.67.1
+transformers==4.52.4
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.13.2
+urllib3==2.4.0
+wrapt==1.17.2
+xxhash==3.5.0
+yarl==1.20.0
+zstandard==0.23.0

search_tools.py

@@ -0,0 +1,53 @@
+from langchain_core.tools import tool
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+# Search engine specifically for LLMs
+# from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_tavily import TavilySearch
+
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    # print(f"Web search query:::::::::::: {query}")
+    search_docs = TavilySearch(max_results=3).invoke({"query":query})
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc["url"]}" page="{doc["title"]}"/>\n{doc["content"]}\n</Document>'
+            for doc in search_docs['results']
+        ])
+    # print(f"Web search result:::::::::::: {formatted_search_docs}")
+    return {"web_results": formatted_search_docs}
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    
+    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}
+
+@tool
+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}