Bug描述

当我构建知识图谱时，我希望Neo4j中的节点包含嵌入向量作为属性。
但是只有id作为"Entity"类型的节点属性。我遵循了示例：https://docs.llamaindex.ai/en/stable/examples/index_structs/knowledge_graph/KnowledgeGraphDemo/
而不是示例中建议的OpenAI模型，我使用了huggingface的"TheBloke/Mistral-7B-Instruct-v0.2-GGUF"和"thenlper/gte-large"作为嵌入模型。
以下是使用Cypher查询从Neo4j检索的一些样本节点。嵌入向量无处可寻。

MATCH (n) RETURN n LIMIT 2;

{
  "identity": 0,
  "labels": [
    "Entity"
  ],
  "properties": {
    "id": "Paul graham"
  },
  "elementId": "4:7dcf7873-019c-40e4-bcdc-9b50ab418257:0"
}
{
  "identity": 1,
  "labels": [
    "Entity"
  ],
  "properties": {
    "id": "Writing"
  },
  "elementId": "4:7dcf7873-019c-40e4-bcdc-9b50ab418257:1"
}

版本

0.1.4

重现步骤

以下是我使用的示例代码

# https://docs.llamaindex.ai/en/stable/examples/index_structs/knowledge_graph/KnowledgeGraphDemo/
import time
import torch
from llama_index.core import Settings
from huggingface_hub import hf_hub_download, snapshot_download
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.llama_cpp import LlamaCPP
from llama_index.llms.llama_cpp.llama_utils import (
    messages_to_prompt,
    completion_to_prompt,
)

from llama_index.core import KnowledgeGraphIndex, SimpleDirectoryReader
from llama_index.core import StorageContext
from llama_index.graph_stores.neo4j import Neo4jGraphStore
from IPython.display import Markdown, display

supported_embed_models = ["thenlper/gte-large"]

supported_llm_models = {
    "TheBloke/Mistral-7B-Instruct-v0.2-GGUF": "mistral-7b-instruct-v0.2.Q5_K_M.gguf",
    "microsoft/Phi-3-mini-4k-instruct-gguf": "Phi-3-mini-4k-instruct-q4.gguf",
}

model_name="TheBloke/Mistral-7B-Instruct-v0.2-GGUF"
embed_model_name="thenlper/gte-large"
temperature=0.0
max_new_tokens=256
context_window=4096
gpu_layers=20
dim=1024
memory_token_limit=4096
sentense_embedding_percentile_cutoff=0.8
similarity_top_k=2
hf_token="<Hugging-face-token>"

MODELS_PATH = "./models"
EMBED_PATH = "./embed_models"

n_gpu_layers = 0
if torch.cuda.is_available():
    print("It is a GPU node, setup GPU.")
    n_gpu_layers = gpu_layers

def get_model_path(model_name):
    filename = supported_llm_models[model_name]
    model_path = hf_hub_download(
        repo_id=model_name,
        filename=filename,
        resume_download=True,
        cache_dir=MODELS_PATH,
        local_files_only=False,
        token=hf_token,
    )
    return model_path

def get_embed_model_path( embed_model):
    embed_model_path = snapshot_download(
        repo_id=embed_model,
        resume_download=True,
        cache_dir=EMBED_PATH,
        local_files_only=False,
        token=hf_token,
    )
    return embed_model_path

llm = LlamaCPP(
    model_path=get_model_path(model_name),
    temperature=temperature,
    max_new_tokens=max_new_tokens,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=context_window,
    # kwargs to pass to __call__()
    # generate_kwargs={"temperature": 0.0, "top_k": 5, "top_p": 0.95},
    generate_kwargs={"temperature": temperature},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    model_kwargs={"n_gpu_layers": n_gpu_layers},
    # transform inputs into Llama2 format
    messages_to_prompt=messages_to_prompt,
    completion_to_prompt=completion_to_prompt,
    verbose=True,
)

embed_model = HuggingFaceEmbedding(
    model_name=embed_model_name,
    cache_folder=EMBED_PATH,
)

Settings.llm = llm
Settings.embed_model = embed_model
Settings.chunk_size = 1024

# copy the essay into the directory: https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt 
documents = SimpleDirectoryReader("./example_data").load_data()

graph_store = Neo4jGraphStore(
    username=<Neo4j-username>,
    password=<Neo4j-password>,
    url=<Neo4j-uri>,
    database=<Neo4j-database>,
)
graph_store.query("MATCH (n) DETACH DELETE n")

storage_context = StorageContext.from_defaults(graph_store=graph_store)

# NOTE: can take a while!
index = KnowledgeGraphIndex.from_documents(
    documents,
    storage_context=storage_context,
    max_triplets_per_chunk=2,
    include_embeddings=True,
    show_progress=True,    
)

query_engine1 = index.as_query_engine(
    include_text=False, response_mode="tree_summarize"
)
query_engine2 = index.as_query_engine(
    include_text=True, response_mode="tree_summarize"
)
query_engine3 = index.as_query_engine(
    include_text=True,
    response_mode="tree_summarize",
    embedding_mode="hybrid",
    similarity_top_k=5,
)

response = query_engine1.query("Tell me more about Interleaf")
display(Markdown(f"<b>{response}</b>"))

response = query_engine2.query(
    "Tell me more about what the author worked on at Interleaf"
)
display(Markdown(f"<b>{response}</b>"))

response = query_engine3.query(
    "Tell me more about what the author worked on at Interleaf"
)
display(Markdown(f"<b>{response}</b>"))

相关日志/回溯

• 无响应*