Stack Overflow
Stack Overflow

Questions tagged [pinecone]

43 questions
0
votes
0 answers

High level overview of how to load dictionary definitions into LangChain?

Either Python or JS LangChain would be fine, but I am trying to wrap my head around how I could create a fantasy language learning AI tutor. This question focuses only on a first part, of loading dictionary definitions into a long term memory. I…
Lance
  • 75,200
  • 93
  • 289
  • 503
0
votes
1 answer

Limited context in OpenAI prompt with embeddings

I am playing around with OpenAI and 10k SEC PDF filings. My stack is OpenAI + Langchain + Pinecone. I am trying to ask a simple question which is "What was AAPL's revenue in 2022" by using embeddings and feeding the context from Pinecone in the…
Martin Linha
  • 979
  • 9
  • 21
0
votes
0 answers

fixing pydantic dependency while working on RAG from pinecone (OpenAIEmbeddings)

How do I get around this error found for importing OpenAIEmbeddings in this pinecone notebook link. The error centers around this import: from langchain.embeddings.openai import OpenAIEmbeddings I first ran into this issue: ERROR: pip's dependency…
sAguinaga
  • 638
  • 13
  • 31
0
votes
1 answer

While creating a pinecone memory for my chatbot, I got an error "consumeToPinecone Error: Request failed with status code 429"

While consuming the pinecone with following code - static async consumeToPinecone(namespace: string, text: string, opts?: { chunkSize?: number; chunkOverlap?: number; openAIApiKey?: string; }) { const { chunkSize = 1200,…
cerebrum infotech
  • 1
  • 1
0
votes
0 answers

langchain and vectorDB always returns different answer

i am playing with langchain, openai, and pinecone (vectordb). i have generated a random list of toys in total 16. Each toy is in a row with a small description. LEGO sets: LEGO offers a wide range of building sets, including themed sets based on…
Khan
  • 1,418
  • 1
  • 25
  • 49
0
votes
0 answers

index.upsert(), Pinecone keeps throwing Type Error: object of type 'NoneType' has no len. Confirmed appropriate data structure

I have written a script that takes embeddings, ids, and metadata from a data table and upserts it to a pinecone index. I have confirmed multiple times that my data structure is correct. I am passing a list of tuples and my embedding vectors are a…
Antwoine Flowers
  • 1
  • 1
0
votes
1 answer

BufferMemory issue with ConversationalRetrievalQAChain in JavaScript/Nodejs

I am using Langchain in Nodejs and following the official documentation to save the conversation context using ConversationalRetrievalQAChain and BufferMemory, and not able to pass the memory object to ConversationalRetrievalQAChain.fromLLM as per…
Wajeeh Aslam
  • 94
  • 1
  • 8
0
votes
0 answers

How to make OpenAI query not talking to its LLM model except for what's in the indexed

Here is what I am doing.. Basically I am retrieving indexed embedding from Pinecone Vector Database and trying to answer a question but when the answer is not available the query grab answers from chatgpt LLM and how can I limit in a way that the…
Andrew Ahn
  • 11
  • 2
0
votes
0 answers

How do you add weights to rank results in pinecone?

I am planning on converting my data currently stored in SQL to Pinecone documents Before converting my data to vectors and passing it to pinecone, my data will look like this: The vendor of the purchase is: ${vendor} The line item of the purchase…
bigpotato
  • 26,262
  • 56
  • 178
  • 334
0
votes
0 answers

How can I get more 'context-aware' results from Vector Similarity Search

I'm writing a document QA program that ingests a pdf document, runs an OpenAI ADA embedding over the documents and then stores the document in a vector db for later querying. The problem is that when I run queries on the index, it gets some of the…
egremont of yorke
  • 893
  • 5
  • 17
0
votes
0 answers

Pinecone MaxRetryError: HTTPSConnectionPool(host='controller."asia-southeast1-gcp-free" ', port=443)

I have this script in my init: pinecone.init( api_key=os.environ["PINECONE_API_KEY"], environment=os.environ["PINECONE_ENVIRONMENT_REGION"] ) And I set PINECONE_ENVIRONMENT_REGION = "asia-southeast1-gcp-free" in my .env But it returns error…
siucat
  • 21
  • 4
0
votes
1 answer

Python pinecone pod not completely full

I am using pinecone in order to store 768-dimensional vectors in a vector database. From the docs, I read that the free tier allows to store up to 100,000 vectors. However, in my case, there seem to be only 1,466 vectors. Also, the dashboard reports…
Polb
  • 640
  • 2
  • 8
  • 21
0
votes
1 answer

If I have connected Open AI and Pinecone, why do I need LangChain?

I'm running a Ruby on Rails app that takes text entries, generates embeddings with OpenAI and sends them to Pinecone. I would like any 'Question' to be asked and for the following to happen: Generate Embedding for the question Query Pinecone with…
MikeHolford
  • 1,851
  • 2
  • 21
  • 32
0
votes
1 answer

How to get ChatGPT to return the source of information returned when trained with own data

I'm trying to use the include my own data to train with ChatGPT by storing the data in a vector database (Pinecone). I'm using the ChatGPT retrieval plugin to vectorise the data and store it in Python. The plugin can be found here:…
Mark
  • 730
  • 1
  • 8
  • 22
0
votes
0 answers

Pinecone ApiException: (400) Reason: Bad Request for Generative QA with OpenAI

I am following the Pinecone user guide to use Generative QA with OpenAI. After having downloaded the dataset and having created a new merged dataset, I rand the following code: # check if index already exists (it shouldn't if this is first time) if…
Emil
  • 1,531
  • 3
  • 22
  • 47
1
2
3