123 questions
Advice
0
votes
0
replies
15
views
RAG with Pinecone + GPT-5 for generating new math problems: incoherent outputs, mixed chunks, and lack of originality
I’m building a tool that generates new mathematics exam problems using an internal database of past problems.
My current setup uses a RAG pipeline, Pinecone as the vector database, and GPT-5 as the ...
Best practices
0
votes
1
replies
105
views
Regarding rag for telephony with deepgram
I'm building a voice-based calling system where users can create AI agents that make outbound phone calls.
The agent uses Deepgram for real-time transcription and ElevenLabs/Cartesia for speech ...
0
votes
0
answers
62
views
Default prompt in langchain creating problem
So I am using pinecone and using self query retrieval with gemini 2.5 pro, with langsmith i came to know the default prompt strictly instructs the ai to use specific comparators
Default Prompt in ...
0
votes
2
answers
56
views
illegal condition for field filter error in pineconeStore similaritySearch
I am building an AI agent and the retrieval node causing issues when I am adding filter object.
Here is the core code or retrieval node :
const filter = {
info: state.info ,
};
const embeddings = ...
-1
votes
1
answer
256
views
ImportError: cannot import name 'Client' from 'pinecone' (unknown location)
The problem with this piece of code is that I am unable to import Client from the pinecone library. I tried to uninstalling and reinstalling different versions none of them worked. I also tried it ...
- 11
0
votes
0
answers
31
views
PineconeDB - Is it possible to change the region of an index?
Our team is currently on the PineconeDB standard plan on uscentral-1. We want to migrate the index to a different region. Is that possible to do? I couldn't find any options to do that in the console.
...
- 2,703
0
votes
1
answer
307
views
AttributeError: module 'pinecone' has no attribute 'Index'
Hi I'm trying to create a pinecone index and write embeddings to it as per below code, but i'm keep getting AttributeError: module 'pinecone' has no attribute 'Index' error, i checked and found that ...
- 139
0
votes
1
answer
105
views
Memory leak due to accumulating threads after add_documents with Pinecone
I have a question regarding thread behavior when embedding data into Pinecone using LangChain.
When I call the add_documents method, I notice that seven new threads are spawned—which seems expected. ...
0
votes
0
answers
89
views
Low Cosine Similarity for Identical Words Using llama-text-embed-v2 in Pinecone
I'm using Pinecone with cosine metric to perform similarity search. I have the word "dog" with the llama-text-embed-v2 and I'm searching the word "dog". I'm expected a cosine ...
- 2,470
3
votes
2
answers
127
views
Accessing Pinecone via PHP
I am having trouble accessing Pinecone via PHP. I tried to follow the examples from the documentation, but it does not seem to work.
<?php
ini_set('display_errors', '1');
ini_set('...
- 114k
0
votes
0
answers
135
views
Entire data is not ingested by AWS Bedrock
I am trying to create a vector data using AWS Bedrock. I am passing a CSV file(stored in S3). While ingesting data, some of the data is randomly dropped by AWS. The csv file has 1000 rows while the ...
0
votes
1
answer
162
views
Upserting in Pinecone takes too long
I'm trying to upsert reviews that i've scraped into pinecone. For the embedding model im using jina-embedding-v3. For 204 reviews this takes around 2.5 hours! in Colab. Tried using GPU but the ...
- 19
0
votes
1
answer
599
views
ValueError: client should be an instance of pinecone.Index, got <class 'pinecone.data.index.Index'>
Please help me fix this:
import os
from pinecone import Pinecone, ServerlessSpec
from langchain.vectorstores import Pinecone as PineconeLangchain
os.environ["PINECONE_API_KEY"] = ...
- 11
2
votes
2
answers
118
views
Python, filter vectors from Pinecone vector store based on a field saved in the metadata of these vectors
I have vectors stored in a Pinecone vector store, each vector represents a content of a pdf file:
Metadata::
hash_code: "d53d7ec8b0e66e9a83a97acda09edd3fe9867cadb42833f9bf5525cc3b89fe2d"
id:...
- 679
-1
votes
1
answer
51
views
Runtime exception System.Text.Json.JsonException: Pinecone databse
I am beginning to learn Vector databases, i am using Pinecone to make the databases, but in this code:
public static async Task SaveToDatabase(List<float> vector)
{
string ApiKey = "...
- 17
-1
votes
1
answer
89
views
'Specified method is not supported' runtime exception
I have seen this question before but i couldn't find a answer that helped my case, but somebody can probably find a way, so i came to ask here. When i run this code:
public static async Task<List&...
- 75
1
vote
0
answers
70
views
Pinecone similarity_search Returning Null
Im learning to use Pinecone but i'm encountering an issue while performing a similarity_search operation in Pinecone. Despite successfully creating and populating the index, the search always returns ...
0
votes
0
answers
75
views
My Pinecone query simply won't return any match (Using Langchain + NodeJS)
I'm using a Node script to load a vectored txt file into a Pinecone index and then trying to query something about the loaded text. My index has the following characteristics:
metric: cosine
...
1
vote
1
answer
155
views
Receiving attribute error that the type object 'Pinecone' has no attribute 'from_existing_index'
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 ...
- 11
0
votes
0
answers
523
views
How to Build a Chatbot That Queries an SQL Database and Uses Vector Search for RAG?
I'm working on a chatbot that answers based on a department store's SQL database, and I need help.
The database looks like this:
If the user asks something like this:
The chatbot should answer like ...
1
vote
0
answers
79
views
Check when vectors are uploaded to Pinecone namespace
I have a pinecone index set up and I am using Langchain to upload my prepared Documents to a certain namespace.
My problem is that, I am returning the PineconeVectorStore and passing that as a ...
- 867
0
votes
1
answer
105
views
AttributeError: type object 'Pinecone' has no attribute 'from_existing_index'
I'm developing a medical chatbot that uses Pinecone for vector storage and SentenceTransformer for generating embeddings. The issue in your code arises from attempting to use a deprecated method ...
0
votes
1
answer
193
views
Upserting into Pinecone Index
I'm trying to upsert some data from a list into a Pinecone index with the following code:
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
model = BertModel.from_pretrained(&...
0
votes
1
answer
264
views
How to get rid of "PineconeApiException: (400)" and "ValueError: Index 'None' not found in your Pinecone project" in jupyter notebook?
I am using this link to learn langhain and pinecone. Just copy pasted the code as bellow:
I am using default PINECONE_API_KEY and using bellow code I am able to create index in pinecone, facing ...
- 99
0
votes
1
answer
796
views
Error saying "AttributeError: 'Document' object has no attribute 'get_doc_id'"
I'm working on using Predibase and LlamaIndex to set up all the moving parts of an RAG system, with Predibase as the LLM provider and currently I'm trying to create the index so that any query I make ...
- 143
1
vote
0
answers
44
views
How can I automatically sync data upsertion from SQLite to my Pinecone index?
I'm working on a project where I need to sync data from a SQLite database to a Pinecone index. I have two Python scripts: one to handle the SQLite database and another to set up and connect to ...
- 11
1
vote
1
answer
90
views
Unclear behaviour of pinecone's load_dataset
In the following program, I have the three functions get_dataset1, get_dataset2, and get_dataset3 that are all very similar. They only differ in when they call len(dataset) and os.path.join = tmp.
The ...
- 489
0
votes
1
answer
584
views
RateLimitError: Error code: 429 while running a RAG application consisting gpt-4oAPI,Pinecone vector store,AzureAIDocumentIntelligenceLoader
Hi I am currently trying to run a RAG application (FAQ chatbot) which consists of 2 UI one where we can separately upload the files and store its embeddings in PineCone Vector store and another where ...
3
votes
1
answer
1k
views
LLamaIndex-ReACT agent talking to itself and hallucinating
I'm new to creating a custom ReACT agent to query my data using the RAG technique.
It turns out that my locally running LLama2 7B model(Using Ollama) does fine with questions about my data(I added the ...
- 31
0
votes
0
answers
188
views
Need to upsert vectors in pinecone DB in Next JS
So I need help pushing vectors into the db, currently something is wrong with the await function here, I am getting an error.
Here is my code for the pinecone.ts file that uploads to the db:
import {
...
1
vote
1
answer
985
views
TypeError: Couldn't build proto file into descriptor pool: duplicate file name opentelemetry/proto/common/v1/common.proto in Docker
I'm encountering an issue when trying to build my Docker image. The error message I receive is:
TypeError: Couldn't build proto file into descriptor pool: duplicate file name opentelemetry/proto/...
0
votes
1
answer
502
views
ScoredVector has no attribute 'metadata' at ['['received_data', 'matches', 0]']['metadata']
I'm building a chatbot RAG using HuggingFace, Mistral, LangChain and Pinecone.
I have a Python Script to watch changes in my MongoDB collection and send the data to Pinecone as a vector.
import os
...
0
votes
2
answers
306
views
Error list index out of range when trying to upsert on pinecone
I'm creating a chatbot RAG using the content from my MongoDB and sending to create vectors on Pinecone.
So my user can ask stuff to my chatbot about his reflections.
Here is my code:
import os
from ...
0
votes
1
answer
918
views
PineconeConfigurationError: You haven't specified an Api-Key
## Vector Search DB In Pinecone
from pinecone import Pinecone, ServerlessSpec
import os
pc = Pinecone(api_key='a561dac3-3246-4aff-97fb-1f648d2ce750')
index_name = "text-embeddings"
if ...
- 17
1
vote
2
answers
328
views
Pinecone serverless from existing index
from flask import Flask, render_template, jsonify, request
from src.helper import download_hugging_face_embeddings
# from langchain.vectorstores import Pinecone
import pinecone
from langchain.prompts ...
0
votes
1
answer
472
views
TypeError: Cannot read properties of undefined (reading '0') open ai
` this is embedding.ts
import { OpenAIApi, Configuration } from "openai-edge";
const config = new Configuration({
apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(...
1
vote
0
answers
192
views
I keep getting Wrong API key error 403 from pinecone
it’s my first time using VDB and I wrote some basic scraping and embedding code for the test. I can’t understand what’s wrong with API, but I keep getting the same error. Here’s my code and the ...
- 23
5
votes
0
answers
233
views
RAG model chat history does not work properly
I am currently trying to develop a sample project by learning RAG. In this code, I aim to chat with a document in Pinecone and while doing this, I try to keep the spoken conversations. These chat ...
- 233
2
votes
1
answer
3k
views
AWS Bedrock Agent Access Denied with Claude 3
I'm using AWS Bedrock with Pinecone as my vector database, and with Claude 2.1, it works smoothly. Still, when I try to update it (or create a new one) using the recently enabled Claude 3.0 Haiku or ...
- 1,895
0
votes
2
answers
533
views
RetrievalQA.from_chain_type showing a validation error of not being able to instantiate abstract
When I am trying to build a RetrievalQA.from_chain_type with my local llm and PineCone VectorDataBase. However, it is not able to create a retriever owing to the error of not being able to instantiate ...
0
votes
1
answer
224
views
Getting topic based data from Pinecone which contains multiple pdf files
I am trying to build a chatbot where I need the bot to response to user query from the data that is stored in vector database like pinecone. Here I want to store pdf of different topic, like different ...
- 1
0
votes
0
answers
341
views
I am unable to perform the vector embeddings with the help of pinecone and python
I have done chunking of the data prior to this and intend to do embeddings and store in pinecone. I have referred to Youtube on this as well and found this code and its not working.
docsearch = pc....
0
votes
1
answer
633
views
Module '"@pinecone-database/pinecone"' has no exported member 'PineconeClient'.ts(2305)
I'm trying to use PineconeClient, importing from "@pinecone-database/pinecone";
But I'm getting the following error:
Module '"@pinecone-database/pinecone"' has no exported member '...
-2
votes
1
answer
354
views
How to create a pinecone client, it's giving error
The is present in the pinecone.ts
import { PineconeClient } from '@pinecone-database/pinecone'
export const getPineconeClient = async () => {
const client = new PineconeClient()
await client....
- 27
0
votes
1
answer
276
views
chatbot that uses only the information in the retriever and nothing more
I need some help,i'm building a chatbot with langchain and Pinecone ; i have tried to use the different chain that i found but none of them actually works fine.What is the best way to create a chain ...
- 1
0
votes
2
answers
135
views
Problem with inserting vectors into PineconeDB
I am trying to insert the vectors into by pinecone database by this lines of code:
console.log('inserting vectors into Pinecone');
const namespace = pineconeIndex.namespace(convertToAscii(filekey)...
1
vote
1
answer
2k
views
Langchain CSVLoader
Not a coding question, but a documentation omission that is nowhere mentioned online at this point. When using the Langchain CSVLoader, which column is being vectorized via the OpenAI embeddings I ...
- 747
2
votes
1
answer
834
views
Recommended approach for managing entries in a vector database when the embeddings are identical but their metadata differs?
In my project, I encounter numerous documents that have identical embeddings but differ in metadata, which might influence retrieval through filtering. (400K documents but only 22040 different ...
- 21
0
votes
0
answers
281
views
processing hundreds of csv files one row at a time for embedding, upload to pinecone using OpenAI embeddings
This is my current code which works for a while and then throws an error of "can't start a new thread." Tried both threading and multi-processing and both cause this error eventually.
def ...
- 747
1
vote
0
answers
266
views
Pinecone query not bringing up any matches?
Here is what I have done - Converted a Snowflake schema into vectors and uploaded them to a Pinecone vector DB.
However when I try to run a query against the Pinecone DB, it does not bring up any ...
