base_index = VectorStoreIndex.from_documents(documents,
storage_context=storage_context,
service_context=service_context,
show_progress=True)VectorStoreIndex.from_documents(documents,
storage_context=storage_context,
service_context=service_context,
show_progress=True)
index = VectorStoreIndex.from_vector_store(vector_store=vector_store,
service_context = service_context)
retriever = index.as_retriever(similarity_top_k = similarity_top_k)query_engine_base = RetrieverQueryEngine.from_args(retriever,
service_context=service_context)
response = query_engine_base.query(query)for node in nodes:
display_source_node(node, source_length=10000)Node ID: d4d67180-71c8-4328-b3f1-1e98fa42ab69 Similarity: 0.8694979150607424 Text: We also list two qualitative examples where safety [...]
Node ID: Source Document: example5.pdf Similarity: Text:
from llama_index.core import Document
from llama_index.core import VectorStoreIndex
index = VectorStoreIndex(embed_model=embed_model)
for chunk in doc.chunks():
index.insert(Document(text=chunk.to_context_text(), extra_info={}))
query_engine = index.as_query_engine()
# Let's run one query
response = query_engine.query("Tell me about Europe.")
print(response)ValueError Traceback (most recent call last)
Cell In[18], line 4
1 from llama_index.core import Document
2 from llama_index.core import VectorStoreIndex
----> 4 index = VectorStoreIndex(embed_model=embed_model)
5 for chunk in doc.chunks():
6 index.insert(Document(text=chunk.to_context_text(), extra_info={}))
...
---> 59 raise ValueError("One of nodes, objects, or index_struct must be provided.")
60 if index_struct is not None and nodes is not None:
61 raise ValueError("Only one of nodes or index_struct can be provided.")
ValueError: One of nodes, objects, or index_struct must be provided.from llama_index.core import SummaryIndex, Document
index = SummaryIndex([])
text_chunks = ["cars are red", "cars are big", "elephants are red"]
doc_chunks = []
for i, text in enumerate(text_chunks):
doc = Document(text=text, id_=f"doc_id_{i}")
doc_chunks.append(doc)
kg_index = KnowledgeGraphIndex.from_documents(documents=doc_chunks,
storage_context=storage_context,
max_triplets_per_chunk=3,
space_name=space_name,
edge_types=edge_types,
rel_prop_names=rel_prop_names,
tags=tags,
llm=llm,
embed_model=embed_model,
include_embeddings=True)
import networkx as nx
G = kg_index.get_networkx_graph()
nx.draw(G, with_labels=True, font_weight='bold')documents = SimpleDirectoryReader("./data").load_data()
kg_index = KnowledgeGraphIndex.from_documents(documents=documents,
storage_context=storage_context,
max_triplets_per_chunk=2,
space_name=space_name,
edge_types=edge_types,
llm=llm,
embed_model=embed_model,
rel_prop_names=rel_prop_names,
tags=tags,
include_embeddings=True)
kg_index.storage_context.persist(persist_dir='./storage_graph')
hybrid_query_engine = kg_index.as_query_engine(include_text=True,
llm=llm,
response_mode="tree_summarize",
embedding_mode="hybrid",
similarity_top_k=3,
explore_global_knowledge=True)
query_text = "What is education?"
response = hybrid_query_engine.query(query_text)Query failed. Query: WITH map{`true`: '-[', `false`: '<-['} AS arrow_l, map{`true`: ']->', `false`: ']-'} AS arrow_r, map{`relationship`: "relationship"} AS edge_type_map MATCH p=(start)-[e:`relationship`*..2]-() WHERE id(start) IN $subjs WITH start, id(start) AS vid, nodes(p) AS nodes, e AS rels [...]from llama_index.llms import OpenAILike
llm = OpenAILike(api_base="http://localhost:8000",\
model="gpt_35_turbo",
api_key="sk-xxx") import pandas as pd
def display_eval_df(query, response, eval_result):
eval_df = pd.DataFrame(
{
"Query": str(query),
"Response": str(response),
"Source": response.source_nodes[0].node.get_content()[:500] + "...",
"Evaluation Result": eval_result.feedback
},
index=[0],
)
eval_df = eval_df.style.set_properties(
**{
"inline-size": "600px",
"overflow-wrap": "break-word",
},
subset=["Response", "Source"]
)
display(eval_df)
prompt_helper = PromptHelper(context_window=4096,
num_output=256,
chunk_overlap_ratio=0.1,
chunk_size_limit=None)
service_context = ServiceContext.from_defaults(llm=llm,
embed_model=embed_model,
prompt_helper=prompt_helper)
query_engine = rag.custom_retriever(query=None,
documents=documents,
method='top_k',
rag=True,
chunk_size=512,
similarity_top_k=1,
eval=True)
faithfulness_evaluator = FaithfulnessEvaluator(service_context=service_context)
response_vector = query_engine.query(eval_questions[1])
eval_result = faithfulness_evaluator.evaluate_response(response=response_vector)
display_eval_df(eval_questions[1], response_vector, eval_result)from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000", api_key="sk-xxx")
response = client.chat.completions.create(model="gpt_35_turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
])
print(response)llm = OpenAI(model="text-davinci-003", temperature=0, max_tokens=256)
embed_model = OpenAIEmbedding()
text_splitter = SentenceSplitter(chunk_size=1024, chunk_overlap=20)
prompt_helper = PromptHelper(
context_window=4096,
num_output=256,
chunk_overlap_ratio=0.1,
chunk_size_limit=None,
)
service_context = ServiceContext.from_defaults(
llm=llm,
embed_model=embed_model,
text_splitter=text_splitter,
prompt_helper=prompt_helper,
)VectorStoreIndex.from_documents(documents,
storage_context=self.storage_context,
service_context=service_context,
show_progress=False)vector_index_chunk = VectorStoreIndex(all_nodes,
service_context=self.service_context,
storage_context=self.storage_context)
index = VectorStoreIndex.from_vector_store(vector_store=self.vector_store,
service_context=self.service_context)
vector_retriever_chunk = vector_index_chunk.as_retriever(similarity_top_k=2)
retriever_chunk = RecursiveRetriever("vector",
retriever_dict={"vector": vector_retriever_chunk},
node_dict=all_nodes_dict,
verbose=True)
if rag:
query_engine_chunk = RetrieverQueryEngine.from_args(retriever_chunk,
service_context=self.service_context)
response = query_engine_chunk.query(query)
return str(response)
else:
result = retriever_chunk.retrieve(query)
res = []
for node in result:
res += [display_source_node_custom(node, 200, True)]
return resValueError: Query id c092cd56-9404-43b8-84a0-d591c2cc2dc9 not found in either `retriever_dict` or `query_engine_dict`.
from openai import OpenAI client = OpenAI(base_url="http://localhost:xxx", api_key="xxx") response = client.embeddings.create(input=["Your string here"], model="Azure-Text-Embedding-ada-002") embedding_vector = response.data[0].embedding
class CustomEmbedding:
def __init__(self, client, model="Azure-Text-Embedding-ada-002"):
self.client = client
self.model = model
def embed(self, texts):
response = self.client.embeddings.create(input=texts, model=self.model)
return [r.embedding for r in response.data]
[...]
client = OpenAI(base_url="http://localhost:xxx", api_key="xxx")
embed_model = CustomEmbedding(client, model="Azure-Text-Embedding-ada-002")AttributeError: 'OpenAI' object has no attribute 'embeddings'
from llama_index import VectorStoreIndex
index = VectorStoreIndex.from_documents(documents,
storage_context=storage_context,
service_context=service_context,
show_progress=True)AttributeError: 'str' object has no attribute 'get_doc_id'