OpenAI 上线新功能力捧 RAG，开发者真的不需要向量数据库了？

pip install openai==1.2.0pip install langchain==0.0.333pip install pymilvus
export OPENAI_API_KEY=xxxx  # Enter your OpenAI API key here

from langchain.vectorstores import Milvusfrom langchain.embeddings import OpenAIEmbeddings

# Prepare retrievervector_db = Milvus(   embedding_function=OpenAIEmbeddings(),   connection_args = {'host': 'localhost', 'port': '19530'}   )retriever = vector_db.as_retriever(search_kwargs={'k': 5})  # change top_k here

from langchain.document_loaders import TextLoaderfrom langchain.text_splitter import RecursiveCharacterTextSplitter

# Parsing and chunking the document.filepath = 'path/to/your/file'doc_data = TextLoader(filepath).load_and_split(   RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)   )

# Embedding and insert chunks into the vector database.vector_db.add_texts([doc.page_content for doc in doc_data])

import osfrom openai import OpenAI

# Setup OpenAI client.client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
# Create an Assistant.my_assistant = client.beta.assistants.create(   name='Chat with a custom retriever',   instructions='You will search for relevant information via retriever and answer questions based on retrieved information.',   tools=[     {       'type': 'function',       'function': {         'name': 'CustomRetriever',         'description': 'Retrieve relevant information from provided documents.',         'parameters': {             'type': 'object',             'properties': {'query': {'type': 'string', 'description': 'The user query'}},             'required': ['query']         },       }     }   ],   model='gpt-4-1106-preview',  # Switch OpenAI model here)

QUERY = 'ENTER YOUR QUESTION HERE'
# Create a thread.my_thread = client.beta.threads.create( messages=[   {     'role': 'user',     'content': QUERY,   } ])
# Invoke a run of my_assistant on my_thread.my_run = client.beta.threads.runs.create(   thread_id=my_thread.id,   assistant_id=my_assistant.id)
# Wait until my_thread halts.while True:   my_run = client.beta.threads.runs.retrieve(thread_id=thread.id, run_id=my_run.id)   if my_run.status != 'queued':       break

# Conduct vector search and parse results when OpenAI Run ready for the next actionif my_run.status == 'requires_action':   tool_outputs = []   for tool_call in my_run.required_action.submit_tool_outputs.tool_calls:       if tool_call.function.name == 'Custom Retriever':           search_res = retriever.get_relevant_documents(QUERY)           tool_outputs.append({               'tool_call_id': tool_call.id,               'output': ('\n\n').join([res.page_content for res in search_res])               })

   # Send retrieval results to your Run service   client.beta.threads.runs.submit_tool_outputs(       thread_id=my_thread.id,       run_id=my_run.id,       tool_outputs=tool_outputs   )

messages = client.beta.threads.messages.list(thread_id=my_thread.id)
for m in messages:   print(f'{m.role}: {m.content[0].text.value}\n')