I’m following a git repo and learning how to make a chatbot using pinecone and llama-2, but I’m getting an attribute error while using the Pinecone module, even though I’ve copied the same code as given in the repo:
These are the dependencies:
from langchain import PromptTemplate
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Pinecone
import pinecone
from langchain.document_loaders import PyPDFLoader, DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.prompts import PromptTemplate
from langchain.llms import CTransformers
from tqdm import tqdm
import os
from pinecone import Pinecone, ServerlessSpec
The code where error occurs:
docsearch=Pinecone.from_existing_index(index_name, embeddings)
query = "What are Allergies"
docs=docsearch.similarity_search(query, k=3)
print("Result", docs)
Getting the following error:
AttributeError Traceback (most recent call last)
<ipython-input-52-de2ccf18d9e8> in <cell line: 1>()
—-> 1 docsearch=Pinecone.from_existing_index(index_name, embeddings)
2
3 query = “What are Allergies”
4
5 docs=docsearch.similarity_search(query, k=3)
AttributeError: type object ‘Pinecone’ has no attribute ‘from_existing_index’
There’s a thread on another website that said that the langchain_pinecone lib and the OG pinecone lib are being confused somehow but I don’t know how to resolve it. I’d appreciate it if I can get a solution this.
Pkun is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Just checked the docs and the code would look like below to do your queries
from pinecone.grpc import PineconeGRPC as Pinecone
# Initialize a Pinecone client with your API key
pc = Pinecone(api_key="YOUR_API_KEY")
query = "Tell me about the tech company known as Apple."
# Convert the query into a numerical vector that Pinecone can search with
query_embedding = pc.inference.embed(
model="multilingual-e5-large",
inputs=[query],
parameters={
"input_type": "query"
}
)
# Search the index for the three most similar vectors
results = index.query(
namespace="example-namespace",
vector=query_embedding[0].values,
top_k=3,
include_values=False,
include_metadata=True
)
print(results)
The docs below are really clear:
Just use pinecone
Langchain Pinecone
you can create the embeddings in your own way as well just adapt to Pinecone format here is how I use it for example (with OpenAI)
res = client.embeddings.create(
input=text_input, model=OPENAI_EMBEDDING_MODEL)