Pinecone Reader¶
In [ ]:
Copied!
%pip install llama-index-readers-pinecone
%pip install llama-index-readers-pinecone
In [ ]:
Copied!
import logging
import sys
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
import logging
import sys
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
In [ ]:
Copied!
api_key = "<api_key>"
api_key = ""
If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
In [ ]:
Copied!
!pip install llama-index
!pip install llama-index
In [ ]:
Copied!
from llama_index.readers.pinecone import PineconeReader
from llama_index.readers.pinecone import PineconeReader
In [ ]:
Copied!
reader = PineconeReader(api_key=api_key, environment="us-west1-gcp")
reader = PineconeReader(api_key=api_key, environment="us-west1-gcp")
In [ ]:
Copied!
# the id_to_text_map specifies a mapping from the ID specified in Pinecone to your text.
id_to_text_map = {
"id1": "text blob 1",
"id2": "text blob 2",
}
# the query_vector is an embedding representation of your query_vector
# Example query vector:
# query_vector=[0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
query_vector = [n1, n2, n3, ...]
# the id_to_text_map specifies a mapping from the ID specified in Pinecone to your text.
id_to_text_map = {
"id1": "text blob 1",
"id2": "text blob 2",
}
# the query_vector is an embedding representation of your query_vector
# Example query vector:
# query_vector=[0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
query_vector = [n1, n2, n3, ...]
In [ ]:
Copied!
# NOTE: Required args are index_name, id_to_text_map, vector.
# In addition, we pass-through all kwargs that can be passed into the `Query` operation in Pinecone.
# See the API reference: https://docs.pinecone.io/reference/query
# and also the Python client: https://github.com/pinecone-io/pinecone-python-client
# for more details.
documents = reader.load_data(
index_name="quickstart",
id_to_text_map=id_to_text_map,
top_k=3,
vector=query_vector,
separate_documents=True,
)
# NOTE: Required args are index_name, id_to_text_map, vector.
# In addition, we pass-through all kwargs that can be passed into the `Query` operation in Pinecone.
# See the API reference: https://docs.pinecone.io/reference/query
# and also the Python client: https://github.com/pinecone-io/pinecone-python-client
# for more details.
documents = reader.load_data(
index_name="quickstart",
id_to_text_map=id_to_text_map,
top_k=3,
vector=query_vector,
separate_documents=True,
)
Create index¶
In [ ]:
Copied!
index = SummaryIndex.from_documents(documents)
index = SummaryIndex.from_documents(documents)
In [ ]:
Copied!
# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("<query_text>")
# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("")
In [ ]:
Copied!
display(Markdown(f"<b>{response}</b>"))
display(Markdown(f"{response}"))