-
Notifications
You must be signed in to change notification settings - Fork 2
/
04 - rag pipeline.py
68 lines (52 loc) · 1.94 KB
/
04 - rag pipeline.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
import os
from dotenv import load_dotenv
from llama_index.core import SimpleDirectoryReader
load_dotenv()
# 1. Load data
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
# 2. Create index
# from llama_index.core import VectorStoreIndex
# index = VectorStoreIndex.from_documents(documents)
# print(documents)
# 3. Create vector store index with Chroma
import chromadb
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.core import StorageContext
# initialize client, setting path to save data
db = chromadb.PersistentClient(path="./chroma_db")
# create collection
chroma_collection = db.get_or_create_collection("quickstart")
# assign chroma as the vector_store to the context
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
# create your index
# index = VectorStoreIndex.from_documents(
# documents, storage_context=storage_context
# )
# load your index from stored vectors
index = VectorStoreIndex.from_vector_store(
vector_store, storage_context=storage_context
)
# 4. Create query engine
from llama_index.core import VectorStoreIndex, get_response_synthesizer
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.core.query_engine import RetrieverQueryEngine
from llama_index.core.postprocessor import SimilarityPostprocessor
# configure retriever
retriever = VectorIndexRetriever(
index=index,
similarity_top_k=10,
)
# configure response synthesizer
response_synthesizer = get_response_synthesizer()
# assemble query engine
query_engine = RetrieverQueryEngine(
retriever=retriever,
response_synthesizer=response_synthesizer,
node_postprocessors=[SimilarityPostprocessor(similarity_cutoff=0.5)],
)
# query
response = query_engine.query("What is the meaning of life?")
print("***********")
print(response)