mirror of
https://github.com/lancedb/lancedb.git
synced 2026-01-08 21:02:58 +00:00
b3bf6386c3
This PR adds the RAG section in the Guides. It includes all the RAGs with code snippet and some advanced techniques which improves RAG.
101 lines
4.1 KiB
Markdown
101 lines
4.1 KiB
Markdown
**Agentic RAG 🤖**
|
||
====================================================================
|
||
Agentic RAG is Agent-based RAG introduces an advanced framework for answering questions by using intelligent agents instead of just relying on large language models. These agents act like expert researchers, handling complex tasks such as detailed planning, multi-step reasoning, and using external tools. They navigate multiple documents, compare information, and generate accurate answers. This system is easily scalable, with each new document set managed by a sub-agent, making it a powerful tool for tackling a wide range of information needs.
|
||
|
||
<figure markdown="span">
|
||
|
||
<figcaption>Agent-based RAG</figcaption>
|
||
</figure>
|
||
|
||
[](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb)
|
||
|
||
Here’s a code snippet for defining retriever using Langchain
|
||
|
||
```python
|
||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||
from langchain_community.document_loaders import WebBaseLoader
|
||
from langchain_community.vectorstores import LanceDB
|
||
from langchain_openai import OpenAIEmbeddings
|
||
|
||
urls = [
|
||
"https://content.dgft.gov.in/Website/CIEP.pdf",
|
||
"https://content.dgft.gov.in/Website/GAE.pdf",
|
||
"https://content.dgft.gov.in/Website/HTE.pdf",
|
||
]
|
||
|
||
|
||
docs = [WebBaseLoader(url).load() for url in urls]
|
||
docs_list = [item for sublist in docs for item in sublist]
|
||
|
||
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
|
||
chunk_size=100, chunk_overlap=50
|
||
)
|
||
doc_splits = text_splitter.split_documents(docs_list)
|
||
|
||
# add documents in LanceDB
|
||
vectorstore = LanceDB.from_documents(
|
||
documents=doc_splits,
|
||
embedding=OpenAIEmbeddings(),
|
||
)
|
||
retriever = vectorstore.as_retriever()
|
||
|
||
```
|
||
|
||
Agent that formulates an improved query for better retrieval results and then grades the retrieved documents
|
||
|
||
```python
|
||
def grade_documents(state) -> Literal["generate", "rewrite"]:
|
||
class grade(BaseModel):
|
||
binary_score: str = Field(description="Relevance score 'yes' or 'no'")
|
||
|
||
model = ChatOpenAI(temperature=0, model="gpt-4-0125-preview", streaming=True)
|
||
llm_with_tool = model.with_structured_output(grade)
|
||
prompt = PromptTemplate(
|
||
template="""You are a grader assessing relevance of a retrieved document to a user question. \n
|
||
Here is the retrieved document: \n\n {context} \n\n
|
||
Here is the user question: {question} \n
|
||
If the document contains keyword(s) or semantic meaning related to the user question, grade it as relevant. \n
|
||
Give a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question.""",
|
||
input_variables=["context", "question"],
|
||
)
|
||
chain = prompt | llm_with_tool
|
||
|
||
messages = state["messages"]
|
||
last_message = messages[-1]
|
||
question = messages[0].content
|
||
docs = last_message.content
|
||
|
||
scored_result = chain.invoke({"question": question, "context": docs})
|
||
score = scored_result.binary_score
|
||
|
||
return "generate" if score == "yes" else "rewrite"
|
||
|
||
|
||
def agent(state):
|
||
messages = state["messages"]
|
||
model = ChatOpenAI(temperature=0, streaming=True, model="gpt-4-turbo")
|
||
model = model.bind_tools(tools)
|
||
response = model.invoke(messages)
|
||
return {"messages": [response]}
|
||
|
||
|
||
def rewrite(state):
|
||
messages = state["messages"]
|
||
question = messages[0].content
|
||
msg = [
|
||
HumanMessage(
|
||
content=f""" \n
|
||
Look at the input and try to reason about the underlying semantic intent / meaning. \n
|
||
Here is the initial question:
|
||
\n ------- \n
|
||
{question}
|
||
\n ------- \n
|
||
Formulate an improved question: """,
|
||
)
|
||
]
|
||
model = ChatOpenAI(temperature=0, model="gpt-4-0125-preview", streaming=True)
|
||
response = model.invoke(msg)
|
||
return {"messages": [response]}
|
||
```
|
||
|
||
[](https://colab.research.google.com/github/lancedb/vectordb-recipes/blob/main/tutorials/Agentic_RAG/main.ipynb) |