多模态模型#

from llama_index.multi_modal_llms.openai import OpenAIMultiModal
from llama_index.core.multi_modal_llms.generic_utils import load_image_urls
from llama_index.core import SimpleDirectoryReader

# load image documents from urls
image_documents = load_image_urls(image_urls)

# load image documents from local directory
image_documents = SimpleDirectoryReader(local_directory).load_data()

# non-streaming
openai_mm_llm = OpenAIMultiModal(
    model="gpt-4-vision-preview", api_key=OPENAI_API_KEY, max_new_tokens=300
)
response = openai_mm_llm.complete(
    prompt="what is in the image?", image_documents=image_documents
)

from llama_index.core.indices import MultiModalVectorStoreIndex
from llama_index.vector_stores.qdrant import QdrantVectorStore
from llama_index.core import SimpleDirectoryReader, StorageContext

import qdrant_client
from llama_index.core import SimpleDirectoryReader

# Create a local Qdrant vector store
client = qdrant_client.QdrantClient(path="qdrant_mm_db")

# if you only need image_store for image retrieval,
# you can remove text_store
text_store = QdrantVectorStore(
    client=client, collection_name="text_collection"
)
image_store = QdrantVectorStore(
    client=client, collection_name="image_collection"
)

storage_context = StorageContext.from_defaults(
    vector_store=text_store, image_store=image_store
)

# Load text and image documents from local folder
documents = SimpleDirectoryReader("./data_folder/").load_data()
# Create the MultiModal index
index = MultiModalVectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
)

from llama_index.multi_modal_llms.openai import OpenAIMultiModal
from llama_index.core import PromptTemplate
from llama_index.core.query_engine import SimpleMultiModalQueryEngine

retriever_engine = index.as_retriever(
    similarity_top_k=3, image_similarity_top_k=3
)

# retrieve more information from the GPT4V response
retrieval_results = retriever_engine.retrieve(response)

# if you only need image retrieval without text retrieval
# you can use `text_to_image_retrieve`
# retrieval_results = retriever_engine.text_to_image_retrieve(response)

qa_tmpl_str = (
    "Context information is below.\n"
    "---------------------\n"
    "{context_str}\n"
    "---------------------\n"
    "Given the context information and not prior knowledge, "
    "answer the query.\n"
    "Query: {query_str}\n"
    "Answer: "
)
qa_tmpl = PromptTemplate(qa_tmpl_str)

query_engine = index.as_query_engine(
    multi_modal_llm=openai_mm_llm, text_qa_template=qa_tmpl
)

query_str = "Tell me more about the Porsche"
response = query_engine.query(query_str)