├── tests ├── __init__.py ├── conftest.py └── test_chains.py ├── agentic_rag ├── graph │ ├── __init__.py │ ├── consts.py │ ├── nodes │ │ ├── __init__.py │ │ ├── retrieve.py │ │ ├── generate.py │ │ ├── web_search.py │ │ └── grade.py │ ├── chains │ │ ├── generation.py │ │ ├── __init__.py │ │ ├── answer_grader.py │ │ ├── retrieval_grader.py │ │ ├── hallucination_grader.py │ │ └── router.py │ ├── state.py │ └── graph.py ├── graph.png ├── main.py └── ingestion.py ├── img └── langgraph_adaptive_rag.png ├── pyproject.toml ├── README.md ├── .gitignore └── LICENSE /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /agentic_rag/graph/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /agentic_rag/graph.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gotsulyakk/agentic-rag/HEAD/agentic_rag/graph.png -------------------------------------------------------------------------------- /img/langgraph_adaptive_rag.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gotsulyakk/agentic-rag/HEAD/img/langgraph_adaptive_rag.png -------------------------------------------------------------------------------- /agentic_rag/graph/consts.py: -------------------------------------------------------------------------------- 1 | RETRIEVE = "retrieve" 2 | GENERATE = "generate" 3 | GRADE_DOCUMENTS = "grade_documents" 4 | WEBSEARCH = "web_search" 5 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- 1 | import sys 2 | import os 3 | 4 | # Add the project root directory to the Python path 5 | project_root = os.path.abspath( 6 | os.path.join(os.path.dirname(__file__), "../agentic_rag") 7 | ) 8 | sys.path.insert(0, project_root) 9 | -------------------------------------------------------------------------------- /agentic_rag/main.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | 3 | from graph.graph import app 4 | 5 | 6 | load_dotenv() 7 | 8 | 9 | if __name__ == "__main__": 10 | question = "What is agent memory in context of LLMs?" 11 | print(app.invoke(input={"question": question})) 12 | -------------------------------------------------------------------------------- /agentic_rag/graph/nodes/__init__.py: -------------------------------------------------------------------------------- 1 | from graph.nodes.generate import generate 2 | from graph.nodes.retrieve import retrieve 3 | from graph.nodes.grade import grade_documents 4 | from graph.nodes.web_search import web_search 5 | 6 | 7 | __all__ = ["generate", "retrieve", "grade_documents", "web_search"] 8 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/generation.py: -------------------------------------------------------------------------------- 1 | from langchain import hub 2 | from langchain_core.output_parsers import StrOutputParser 3 | from langchain_openai import ChatOpenAI 4 | 5 | 6 | llm = ChatOpenAI(temperature=0) 7 | prompt = hub.pull("rlm/rag-prompt") 8 | 9 | generation_chain = prompt | llm | StrOutputParser() 10 | -------------------------------------------------------------------------------- /agentic_rag/graph/state.py: -------------------------------------------------------------------------------- 1 | from typing import List, TypedDict 2 | 3 | 4 | class GraphState(TypedDict): 5 | """ 6 | Represents a state of a graph. 7 | 8 | Attributes: 9 | question: Question 10 | generation: LLM Generation 11 | use_web_search: wether to use web search 12 | documents: List of documents 13 | """ 14 | 15 | question: str 16 | generation: str 17 | use_web_search: bool 18 | documents: List[str] 19 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/__init__.py: -------------------------------------------------------------------------------- 1 | from graph.chains.generation import generation_chain 2 | from graph.chains.hallucination_grader import hallucination_grader 3 | from graph.chains.retrieval_grader import retrieval_grader 4 | from graph.chains.answer_grader import answer_grader 5 | from graph.chains.router import question_router 6 | 7 | 8 | __all__ = [ 9 | "generation_chain", 10 | "hallucination_grader", 11 | "retrieval_grader", 12 | "answer_grader", 13 | "question_router", 14 | ] 15 | -------------------------------------------------------------------------------- /agentic_rag/graph/nodes/retrieve.py: -------------------------------------------------------------------------------- 1 | from typing import Any, Dict 2 | 3 | from graph.state import GraphState 4 | from ingestion import retriever 5 | 6 | 7 | def retrieve(state: GraphState) -> Dict[str, Any]: 8 | """ 9 | Retrieve documents from the retriever. 10 | 11 | Args: 12 | state: The current state of the graph. 13 | 14 | Returns: 15 | A dictionary containing the retrieved documents and the question 16 | """ 17 | print("---RETRIEVE---") 18 | question = state["question"] 19 | documents = retriever.invoke(question) 20 | return {"documents": documents, "question": question} 21 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [tool.poetry] 2 | name = "advanced-rag" 3 | version = "0.1.0" 4 | description = "" 5 | authors = ["gotsulyakk"] 6 | readme = "README.md" 7 | 8 | [tool.poetry.dependencies] 9 | python = "3.12.3" 10 | beautifulsoup4 = "4.12.3" 11 | langchain = "0.2.3" 12 | langgraph = "0.0.67" 13 | langchainhub = "0.1.20" 14 | langchain-community = "0.2.4" 15 | black = "24.4.2" 16 | isort = "5.13.2" 17 | tavily-python = "0.3.3" 18 | langchain-chroma = "0.1.1" 19 | python-dotenv = "1.0.1" 20 | pytest = "8.2.2" 21 | langchain-openai = "0.1.8" 22 | 23 | 24 | [build-system] 25 | requires = ["poetry-core"] 26 | build-backend = "poetry.core.masonry.api" 27 | -------------------------------------------------------------------------------- /agentic_rag/graph/nodes/generate.py: -------------------------------------------------------------------------------- 1 | from typing import Any, Dict 2 | 3 | from graph.state import GraphState 4 | from graph.chains.generation import generation_chain 5 | 6 | 7 | def generate(state: GraphState) -> Dict[str, Any]: 8 | """ 9 | Generate a response to the user question. 10 | 11 | Args: 12 | state (dict): The current state of the graph. 13 | 14 | Returns: 15 | state (dict): A dictionary containing the generated response and the question 16 | """ 17 | print("---GENERATE---") 18 | question = state["question"] 19 | documents = state["documents"] 20 | generation = generation_chain.invoke({"context": documents, "question": question}) 21 | return {"generation": generation, "documents": documents, "question": question} 22 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/answer_grader.py: -------------------------------------------------------------------------------- 1 | from langchain_core.prompts import ChatPromptTemplate 2 | from langchain_core.pydantic_v1 import BaseModel, Field 3 | from langchain_core.runnables import RunnableSequence 4 | from langchain_openai import ChatOpenAI 5 | 6 | 7 | class GradeAnswer(BaseModel): 8 | """Binary score for assessing the answer is relevant to the question.""" 9 | 10 | binary_score: str = Field( 11 | description="Answer addresses the question, 'yes' or 'no'." 12 | ) 13 | 14 | 15 | llm = ChatOpenAI(temperature=0) 16 | structured_llm_grader = llm.with_structured_output(GradeAnswer) 17 | 18 | message = """You are a grader assessing whether an answer addresses / resolves a question \n 19 | Give a binary score 'yes' or 'no'. Yes' means that the answer resolves the question.""" 20 | answer_prompt = ChatPromptTemplate.from_messages( 21 | [ 22 | ("system", message), 23 | ("human", "User question: {question} \n\n LLM generated answer: {generation}"), 24 | ] 25 | ) 26 | 27 | answer_grader: RunnableSequence = answer_prompt | structured_llm_grader 28 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/retrieval_grader.py: -------------------------------------------------------------------------------- 1 | from langchain_core.prompts import ChatPromptTemplate 2 | from langchain_core.pydantic_v1 import BaseModel, Field 3 | from langchain_openai import ChatOpenAI 4 | 5 | 6 | llm = ChatOpenAI(temperature=0) 7 | 8 | 9 | class GradeDocuments(BaseModel): 10 | """Binary score for the relevance check of retrieved documents""" 11 | 12 | binary_score: str = Field( 13 | description="Documents are relevant to the question? 'yes' or 'no'", 14 | ) 15 | 16 | 17 | structured_llm_grader = llm.with_structured_output(GradeDocuments) 18 | 19 | message = """You are a grader assessing relevance of a retrieved document to a user question. \n 20 | If the document contains keyword(s) or semantic meaning related to the question, grade it as relevant. \n 21 | Give a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question.""" 22 | grade_prompt = ChatPromptTemplate.from_messages( 23 | [ 24 | ("system", message), 25 | ("human", "Retrieved document: \n\n {document} \n\n User question: {question}"), 26 | ] 27 | ) 28 | 29 | retrieval_grader = grade_prompt | structured_llm_grader 30 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/hallucination_grader.py: -------------------------------------------------------------------------------- 1 | from langchain_core.prompts import ChatPromptTemplate 2 | from langchain_core.pydantic_v1 import BaseModel, Field 3 | from langchain_core.runnables import RunnableSequence 4 | from langchain_openai import ChatOpenAI 5 | 6 | 7 | class GradeHallucinations(BaseModel): 8 | """Binary score for hallucination present in generated answer.""" 9 | 10 | binary_score: str = Field( 11 | description="Answer is grounded in the facts, 'yes' or 'no'." 12 | ) 13 | 14 | 15 | llm = ChatOpenAI(temperature=0) 16 | 17 | structured_llm_grader = llm.with_structured_output(GradeHallucinations) 18 | 19 | message = """You are a grader assessing whether an LLM generation is grounded in / supported by a set of retrieved facts. \n 20 | Give a binary score 'yes' or 'no'. 'Yes' means that the answer is grounded in / supported by the set of facts.""" 21 | hallucination_prompt = ChatPromptTemplate.from_messages( 22 | [ 23 | ("system", message), 24 | ("human", "Set of facts: \n\n {documents} \n\n LLM generation: {generation}"), 25 | ] 26 | ) 27 | 28 | hallucination_grader: RunnableSequence = hallucination_prompt | structured_llm_grader 29 | -------------------------------------------------------------------------------- /agentic_rag/graph/chains/router.py: -------------------------------------------------------------------------------- 1 | from typing import Literal 2 | 3 | from langchain_core.prompts import ChatPromptTemplate 4 | from langchain_core.pydantic_v1 import BaseModel, Field 5 | from langchain_openai import ChatOpenAI 6 | 7 | 8 | class RouteQuery(BaseModel): 9 | """Route a user query to the most relevant datasource.""" 10 | 11 | datasource: Literal["vectorstore", "web_search"] = Field( 12 | ..., 13 | description="Route the user query to the vectorstore or websearch. Avalable options are 'vectorstore' or 'web_search'", 14 | ) 15 | 16 | 17 | llm = ChatOpenAI(temperature=0) 18 | structured_llm_router = llm.with_structured_output(RouteQuery) 19 | 20 | message = """You are an expert at routing a user question to a vectorstore or web search. 21 | The vectorstore contains documents related to machine learning concepts such as: agents, prompt engineering, and adversarial attacks. 22 | Use the vectorstore for questions on these topics. For ANY other question, choose web-search route.""" 23 | router_prompt = ChatPromptTemplate.from_messages( 24 | [("system", message), ("human", "{question}")] 25 | ) 26 | 27 | question_router = router_prompt | structured_llm_router 28 | -------------------------------------------------------------------------------- /agentic_rag/ingestion.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | from langchain.text_splitter import RecursiveCharacterTextSplitter 3 | from langchain_community.document_loaders import WebBaseLoader 4 | from langchain_chroma import Chroma 5 | from langchain_openai import OpenAIEmbeddings 6 | 7 | load_dotenv() 8 | 9 | urls = [ 10 | "https://lilianweng.github.io/posts/2023-06-23-agent/", 11 | "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/", 12 | "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/", 13 | ] 14 | 15 | docs = [WebBaseLoader(url).load() for url in urls] 16 | docs_list = [item for sublist in docs for item in sublist] 17 | 18 | text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder( 19 | chunk_size=512, chunk_overlap=0 20 | ) 21 | doc_splits = text_splitter.split_documents(docs_list) 22 | 23 | vectorstore = Chroma.from_documents( 24 | documents=doc_splits, 25 | collection_name="rag-chroma", 26 | embedding=OpenAIEmbeddings(), 27 | persist_directory="./.chroma", 28 | ) 29 | retriever = Chroma( 30 | collection_name="rag-chroma", 31 | persist_directory="./.chroma", 32 | embedding_function=OpenAIEmbeddings(), 33 | ).as_retriever() 34 | -------------------------------------------------------------------------------- /agentic_rag/graph/nodes/web_search.py: -------------------------------------------------------------------------------- 1 | from typing import Any, Dict 2 | 3 | from langchain.schema import Document 4 | from langchain_community.tools.tavily_search import TavilySearchResults 5 | 6 | from graph.state import GraphState 7 | 8 | 9 | web_search_tool = TavilySearchResults(max_results=3) 10 | 11 | 12 | def web_search(state: GraphState) -> Dict[str, Any]: 13 | """ 14 | Search the web for documents. 15 | 16 | Args: 17 | state (dict): The current state of the graph. 18 | 19 | Returns: 20 | state (dict): A dictionary containing the retrieved documents and the question 21 | """ 22 | print("---WEB SEARCH---") 23 | question = state["question"] 24 | documents = state["documents"] # only relevant documents 25 | 26 | tavily_results = web_search_tool.invoke({"query": question}) 27 | 28 | # get one huge string with all the results 29 | tavily_results_joined = "\n".join([res["content"] for res in tavily_results]) 30 | 31 | # create a document object 32 | web_search_result = Document(page_content=tavily_results_joined) 33 | 34 | # append web search to the list of documents 35 | if documents is not None: 36 | documents.append(web_search_result) 37 | else: 38 | documents = [web_search_result] 39 | 40 | return {"documents": documents, "question": question} 41 | -------------------------------------------------------------------------------- /agentic_rag/graph/nodes/grade.py: -------------------------------------------------------------------------------- 1 | from typing import Any, Dict 2 | 3 | from graph.chains.retrieval_grader import retrieval_grader 4 | from graph.state import GraphState 5 | 6 | 7 | def grade_documents(state: GraphState) -> Dict[str, Any]: 8 | """ 9 | Determines whether the retrieved documents are relevant to the user question. 10 | If any document is not relevant, we will set a flag to run web search. 11 | 12 | Args: 13 | state (dict): The current state of the graph. 14 | 15 | Returns: 16 | state (dict): Filtered out irrelevant documents and updated use_web_search state. 17 | """ 18 | print("---GRADE DOCUMENTS---") 19 | question = state["question"] 20 | documents = state["documents"] 21 | 22 | filtered_documents = [] 23 | use_web_search = False 24 | for doc in documents: 25 | result = retrieval_grader.invoke( 26 | {"question": question, "document": doc.page_content} 27 | ) 28 | grade = result.binary_score 29 | if grade.lower() == "yes": 30 | print("---DOCUMENT IS RELEVANT---") 31 | filtered_documents.append(doc) 32 | else: 33 | print("---DOCUMENT IS NOT RELEVANT---") 34 | use_web_search = True 35 | continue 36 | return { 37 | "documents": filtered_documents, 38 | "use_web_search": use_web_search, 39 | "question": question, 40 | } 41 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Agentic RAG 2 | 3 | ## Description 4 | Using LangGraph to build agentic workflow based on 5 | - Corrective-RAG (CRAG) paper uses self-grading on retrieved documents and web-search fallback if documents are not relevant. 6 | - Self-RAG paper adds self-grading on generations for hallucinations and for ability to answer the question. 7 | - Adaptive RAG paper routes queries between different RAG approaches based on their complexity. 8 | 9 | ![Advanced RAG](img/langgraph_adaptive_rag.png) 10 | 11 | LangGraph built-in mermaid visualization 12 | 13 | ![LangGraphRAG](agentic_rag/graph.png) 14 | ## Installation 15 | 16 | To get started, follow these steps: 17 | 18 | 1. **Clone the repository**: 19 | ```sh 20 | git clone https://github.com/gotsulyakk/agentic-rag.git 21 | cd agentic-rag 22 | ``` 23 | 24 | 2. **Install dependencies**: 25 | [Poetry](https://python-poetry.org/) is recommended for dependency management. 26 | ```sh 27 | poetry install 28 | ``` 29 | 30 | 3. **Set up environment variables**: 31 | Create a `.env` file in the root directory and add necessary environment variables. 32 | ```sh 33 | OPENAI_API_KEY 34 | TAVILY_API_KEY 35 | LANGCHAIN_API_KEY 36 | LANGCHAIN_TRACING_V2 37 | LANGCHAIN_PROJECT 38 | ``` 39 | 40 | ## Usage 41 | 42 | To run the main application: 43 | 44 | ```sh 45 | cd agentic_rag 46 | poetry run python main.py 47 | ``` 48 | 49 | ## Acknowledgements 50 | 51 | - https://www.youtube.com/watch?v=NZbgduKl9Zk 52 | - https://www.youtube.com/watch?v=zXFxmI9f06M 53 | - https://github.com/mistralai/cookbook/tree/main/third_party/langchain -------------------------------------------------------------------------------- /agentic_rag/graph/graph.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | 3 | from langgraph.graph import END, StateGraph 4 | 5 | from graph.state import GraphState 6 | from graph.consts import RETRIEVE, GENERATE, GRADE_DOCUMENTS, WEBSEARCH 7 | from graph.chains import hallucination_grader, answer_grader, question_router 8 | from graph.nodes import generate, grade_documents, retrieve, web_search 9 | 10 | 11 | load_dotenv() 12 | 13 | 14 | def decide_to_generate(state): 15 | print("---ASSESS GRADED DOCUMENTS---") 16 | 17 | if state["use_web_search"]: 18 | print("---DECISION: NOT ALL DOCUMENTS ARE RELEVANT, GO TO WEB---") 19 | return WEBSEARCH 20 | else: 21 | print("---DECISION: GENERATE---") 22 | return GENERATE 23 | 24 | 25 | def grade_generation_grounded_in_documents_and_question(state: GraphState): 26 | print("---CHECK HALLUCINATIONS---") 27 | 28 | question = state["question"] 29 | documents = state["documents"] 30 | generation = state["generation"] 31 | 32 | score = hallucination_grader.invoke( 33 | {"documents": documents, "generation": generation} 34 | ) 35 | if hallucination_grade := score.binary_score: 36 | print("---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---") 37 | print("---CHECK ANSWER---") 38 | score = answer_grader.invoke({"question": question, "generation": generation}) 39 | if answer_grade := score.binary_score: 40 | print("---DECISION: ANSWER ADDRESSES THE USER QUESTION---") 41 | return "useful" 42 | else: 43 | print("---DECISION: ANSWER DOES NOT ADDRESS THE USER QUESTION---") 44 | return "not_useful" 45 | else: 46 | print("---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS---") 47 | return "not_supported" 48 | 49 | 50 | def route_question(state: GraphState): 51 | print("---ROUTE QUESTION---") 52 | question = state["question"] 53 | 54 | source = question_router.invoke({"question": question}) 55 | 56 | if source.datasource == WEBSEARCH: 57 | print("---DECISION: ROUTE QUESTION TO WEB SEARCH---") 58 | return WEBSEARCH 59 | elif source.datasource == "vectorstore": 60 | print("---DECISION: ROUTE QUESTION TO RAG---") 61 | return RETRIEVE 62 | 63 | 64 | flow = StateGraph(state_schema=GraphState) 65 | 66 | flow.add_node(RETRIEVE, retrieve) 67 | flow.add_node(GRADE_DOCUMENTS, grade_documents) 68 | flow.add_node(GENERATE, generate) 69 | flow.add_node(WEBSEARCH, web_search) 70 | 71 | flow.set_conditional_entry_point( 72 | route_question, path_map={RETRIEVE: RETRIEVE, WEBSEARCH: WEBSEARCH} 73 | ) 74 | 75 | flow.add_edge(RETRIEVE, GRADE_DOCUMENTS) 76 | 77 | flow.add_conditional_edges( 78 | GRADE_DOCUMENTS, 79 | decide_to_generate, 80 | path_map={WEBSEARCH: WEBSEARCH, GENERATE: GENERATE}, 81 | ) 82 | flow.add_conditional_edges( 83 | GENERATE, 84 | grade_generation_grounded_in_documents_and_question, 85 | path_map={"useful": END, "not_useful": WEBSEARCH, "not_supported": GENERATE}, 86 | ) 87 | 88 | flow.add_edge(WEBSEARCH, GENERATE) 89 | flow.add_edge(GENERATE, END) 90 | 91 | app = flow.compile() 92 | app.get_graph().draw_mermaid_png(output_file_path="graph.png") 93 | -------------------------------------------------------------------------------- /tests/test_chains.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | from pprint import pprint 3 | 4 | load_dotenv() 5 | 6 | from agentic_rag.graph.chains.retrieval_grader import GradeDocuments, retrieval_grader 7 | from agentic_rag.graph.chains.hallucination_grader import ( 8 | GradeHallucinations, 9 | hallucination_grader, 10 | ) 11 | from agentic_rag.graph.chains.answer_grader import GradeAnswer, answer_grader 12 | from agentic_rag.graph.chains.generation import generation_chain 13 | from agentic_rag.graph.chains.router import RouteQuery, question_router 14 | 15 | from agentic_rag.ingestion import retriever 16 | 17 | 18 | # def test_retrieval_grader_answer_yes() -> None: 19 | # question = "agent memory" 20 | # docs = retriever.invoke(question) 21 | # doc_text = docs[1].page_content 22 | 23 | # res: GradeDocuments = retrieval_grader.invoke( 24 | # {"question": question, "document": doc_text} 25 | # ) 26 | 27 | # # it just works randomly, so, ignore it 28 | # # assert str(res.binary_score).lower() == "yes" 29 | # # instead, just check if it is 'yes' or 'no' 30 | # assert str(res.binary_score).lower() in ["yes", "no"] 31 | 32 | 33 | # def test_retrieval_grader_answer_no() -> None: 34 | # question = "donald trump" 35 | # docs = retriever.invoke(question) 36 | # doc_text = docs[1].page_content 37 | 38 | # res: GradeDocuments = retrieval_grader.invoke( 39 | # {"question": question, "document": doc_text} 40 | # ) 41 | 42 | # # it just works randomly, so, ignore it 43 | # # assert str(res.binary_score).lower() == "no" 44 | # # instead, just check if it is 'yes' or 'no' 45 | # assert str(res.binary_score).lower() in ["yes", "no"] 46 | 47 | 48 | def test_retrieval_grader_answer_yes_or_no() -> None: 49 | question = "agent memory" 50 | docs = retriever.invoke(question) 51 | doc_text = docs[1].page_content 52 | 53 | res: GradeDocuments = retrieval_grader.invoke( 54 | {"question": question, "document": doc_text} 55 | ) 56 | 57 | assert str(res.binary_score).lower() in ["yes", "no"] 58 | 59 | 60 | def test_generation_chain() -> None: 61 | question = "agent memory" 62 | docs = retriever.invoke(question) 63 | 64 | generation = generation_chain.invoke({"context": docs, "question": question}) 65 | 66 | pprint(generation) 67 | assert generation is not None 68 | 69 | 70 | def test_hallucination_grader_answer_yes_or_no() -> None: 71 | question = "agent memory" 72 | docs = retriever.invoke(question) 73 | 74 | generation = generation_chain.invoke({"context": docs, "question": question}) 75 | res: GradeHallucinations = hallucination_grader.invoke( 76 | {"documents": docs, "generation": generation} 77 | ) 78 | 79 | assert str(res.binary_score).lower() in ["yes", "no"] 80 | 81 | 82 | def test_answer_grader_answer_yes_or_no() -> None: 83 | question = "agent memory" 84 | docs = retriever.invoke(question) 85 | 86 | generation = generation_chain.invoke({"context": docs, "question": question}) 87 | res: GradeAnswer = answer_grader.invoke( 88 | {"question": question, "generation": generation} 89 | ) 90 | 91 | assert str(res.binary_score).lower() in ["yes", "no"] 92 | 93 | 94 | def test_question_router_to_vectorstore() -> None: 95 | question = "agent memory" 96 | 97 | res: RouteQuery = question_router.invoke({"question": question}) 98 | 99 | assert res.datasource == "vectorstore" 100 | 101 | 102 | def test_question_router_to_websearch() -> None: 103 | question = "Where is John Paul II Catholic High School located?" 104 | 105 | res: RouteQuery = question_router.invoke({"question": question}) 106 | 107 | assert res.datasource == "web_search" 108 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 110 | .pdm.toml 111 | .pdm-python 112 | .pdm-build/ 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | 164 | # ChromaDB 165 | .chroma/ 166 | 167 | .DS_Store -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------