test

.gitattributes

@@ -33,5 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-生成特定图片.png filter=lfs diff=lfs merge=lfs -text
-cheatsheet-transformers-large-language-models.pdf filter=lfs diff=lfs merge=lfs -text

agent.py

@@ -1,216 +0,0 @@
-
-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
-
-load_dotenv()
-
-
-@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
-
-@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 web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
-    Args:
-        query: The search query."""
-    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}
-
-@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}
-
-
-# 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)
-
-# build a retriever with existing supabase
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-supabase: Client = create_client(
-    os.environ.get("SUPABASE_URL"), 
-    os.environ.get("SUPABASE_SERVICE_KEY"))
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding= embeddings,
-    table_name=os.getenv('TABLE_NAME'),
-    query_name=os.getenv('QUERY_NAME'),
-)
-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 = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    wiki_search,
-    web_search,
-    arvix_search,
-]
-
-# Build graph function
-def build_graph(provider: str = "groq"):
-    """Build the graph"""
-    # Load environment variables from .env file
-    if provider == "google":
-        # Google Gemini
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    elif provider == "groq":
-        print("choose groq=====================================")
-        # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
-    elif provider == "huggingface":
-        print("choose huggingface===============================================")
-        # TODO: Add huggingface endpoint
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                model='Meta-DeepLearning/llama-2-7b-chat-hf',
-                endpoint_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
-    llm_with_tools = llm.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}
-
-    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")
-
-    # Compile graph
-    return builder.compile()
-
-# test
-if __name__ == "__main__":
-    question = "What's the last line of the rhyme under the flavor name on the headstone visible in the background of the photo of the oldest flavor's headstone in the Ben & Jerry's online flavor graveyard as of the end of 2022?"
-    # Build the graph
-    graph = build_graph(provider="groq")
-    # Run the graph
-    messages = [HumanMessage(content=question)]
-    messages = graph.invoke({"messages": messages})
-    for m in messages["messages"]:
-        m.pretty_print()

app.py

@@ -3,8 +3,6 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-from agent import build_graph
-from langchain_core.messages import HumanMessage, SystemMessage
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -15,17 +13,11 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-        self.graph = build_graph()
-        
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        
-        messages = [HumanMessage(content=question)]
-        messages = self.graph.invoke({"messages": messages})
-        answer = messages['messages'][-1].content.split("FINAL ANSWER: ")[-1]
-
-        print(f"Agent returning answer: {answer}")
-        return answer
+        fixed_answer = "This is a default answer."
+        print(f"Agent returning fixed answer: {fixed_answer}")
+        return fixed_answer
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """

cheatsheet-transformers-large-language-models.pdf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5f4cba7c54bbe86caf70122b665b1b14d51abad2634bf5c6481eb62fd6a1a3f
-size 1587084

requirements.txt

@@ -1,23 +1,2 @@
 gradio
-requests
-langchain
-langchain-community
-langchain-core
-langchain-google-genai
-langchain-huggingface
-langchain-groq
-langchain-tavily
-langchain-chroma
-langgraph
-huggingface_hub
-supabase
-arxiv
-pymupdf
-wikipedia
-pgvector
-python-dotenv
-gradio[oauth]>=4.25.0
-sentence-transformers
-numpy<2
-duckduckgo-search
-langchain_openai
+requests

retriever.py

@@ -1,57 +0,0 @@
-#build retriever on supabase
-#create project, table, indexes, and functions
-#create client with url and key
-#insert data with embedding
-#
-# Load metadata.jsonl
-import json
-import os
-from dotenv import load_dotenv
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain_community.vectorstores import SupabaseVectorStore
-from supabase.client import Client, create_client
-from langchain.schema import Document
-
-# Load the metadata.jsonl file
-with open('metadata.jsonl', 'r') as jsonl_file:
-    json_list = list(jsonl_file)
-
-json_QA = []
-for json_str in json_list:
-    json_data = json.loads(json_str)
-    json_QA.append(json_data)
-
-### build a vector database based on the metadata.jsonl
-# https://python.langchain.com/docs/integrations/vectorstores/supabase/
-
-load_dotenv()
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-
-supabase_url = os.environ.get("SUPABASE_URL")
-supabase_key = os.environ.get("SUPABASE_SERVICE_KEY")
-supabase: Client = create_client(supabase_url, supabase_key)
-
-# wrap the metadata.jsonl's questions and answers into a list of document
-
-docs = []
-for sample in json_QA:
-    content = f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}"
-    doc = {
-        "content" : content,
-        "metadata" : { # meatadata的格式必须时source键，否则会报错
-            "source" : sample['task_id']
-        },
-        "embedding" : embeddings.embed_query(content),
-    }
-    docs.append(doc)
-
-table_name = os.environ.get('TABLE_NAME')
-# upload the documents to the vector database
-try:
-    response = (
-        supabase.table("documents")
-        .insert(docs)
-        .execute()
-    )
-except Exception as exception:
-    print("Error inserting data into Supabase:", exception)

steps.txt

@@ -1,43 +0,0 @@
-#give yourself more patiences
-
-1. explore metadata, check each keys
-
-2. define retriever
-supabase?
-relational database?, embeddings, content, id, ...
-create a project, and a table + columns first emm...
-https://supabase.com/dashboard/project/ohzwldyjckkuzbybaixs/editor/17248
-enable vector in extensions under database
-
-create table public.documents (
-  id bigint generated by default as identity primary key,
-  content text,
-  metadata json,
-  embedding vector(768),
-  similarity float
-);
-
-create index for embedding!!!
-
-add functions, advanced settings, sql language
-
-create index on documents using hnsw (embedding vector_ip_ops);
-alter table documents enable row level security;
-create function match_documents_langchain (
-  query_embedding vector (768)
-)
-returns setof documents
-language plpgsql
-as $$
-begin
-  return query
-  select *
-  from documents
-  order by documents.embedding <#> query_embedding
-  limit 1;
-end;
-$$;
-
-3. define agent
-
-4. define gradio

system_prompt.txt

@@ -1,46 +0,0 @@
-
-
-You are a helpful assistant tasked with answering questions using a set of tools.
-If the tool is not available, you can try to find the information online. You can also use your own knowledge to answer the question. 
-YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
-Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
-Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
-FINAL ANSWER: [YOUR FINAL ANSWER]. 
-
-==========================
-Here is a few examples showing you how to answer the question step by step.
-
-
-Question 1: Compute the check digit the Tropicos ID for the Order Helotiales would have if it were an ISBN-10 number.
-Steps:
-1. Search "Tropicos ID Order Helotiales"
-2. Find the correct ID on the first result
-3. Search "isbn 10 check digit calculator" or calculate check digit by hand
-Tools:
-1. web browser
-2. search engine
-3. calculator
-Final Answer: 3
-
-Question 2: What's the last line of the rhyme under the flavor name on the headstone visible in the background of the photo of the oldest flavor's headstone in the Ben & Jerry's online flavor graveyard as of the end of 2022?
-Steps:
-1. Searched "ben and jerrys flavor graveyard" on Google search.
-2. Opened "Flavor Graveyard" on www.benjerry.com.
-3. Opened each flavor to find the oldest one (Dastardly Mash).
-4. Deciphered the blurry name on the headstone behind it (Miz Jelena's Sweet Potato Pie).
-5. Scrolled down to Miz Jelena's Sweet Potato Pie.
-6. Copied the last line of the rhyme.
-7. (Optional) Copied the URL.
-8. Searched "internet archive" on Google search.
-9. Opened the Wayback Machine.
-10. Entered the URL.
-11. Loaded the last 2022 page.
-12. Confirmed the information was the same.
-Tools:
-1. Image recognition tools
-2. Web browser
-3. Search engine
-Final Answer: So we had to let it die.
-
-==========================
-Now, please answer the following question step by step.