# \#sentence-transformer **URL:** https://community.pinecone.io/tag/sentence-transformer/3.md [Latest](https://community.pinecone.io/latest.md) · [Categories](https://community.pinecone.io/categories.md) · [Tags](https://community.pinecone.io/tags.md) --- ## [Is there an API for PHP?](https://community.pinecone.io/t/is-there-an-api-for-php/6962)
**Author:** [@shlomo1](https://community.pinecone.io/u/shlomo1)\ **Replies:** 8\ **Last updated:** [April 9, 2025, 8:28pm UTC](https://community.pinecone.io/t/is-there-an-api-for-php/6962 "2025-04-09T20:28:17Z")
My projet is based on PHP. Is there and SDK for it? Are there exaples using PHP? --- ## [Storing metadata in pinecone cloud DB for each Resume](https://community.pinecone.io/t/storing-metadata-in-pinecone-cloud-db-for-each-resume/7685)
**Author:** [@vijay.sagi](https://community.pinecone.io/u/vijay.sagi)\ **Replies:** 2\ **Last updated:** [March 19, 2025, 12:02pm UTC](https://community.pinecone.io/t/storing-metadata-in-pinecone-cloud-db-for-each-resume/7685 "2025-03-19T12:02:42Z")
Hi, I have 50 resumes in pdf format, i am able to read all pdf content as chunks and store in the vector database and able to retrieve based the LLM Query sucessfully. The challenge is, how can i store each resume meta… --- ## [AttributeError while performing Pinecone.from\_texts](https://community.pinecone.io/t/attributeerror-while-performing-pinecone-from-texts/5239)
**Author:** [@light0-0](https://community.pinecone.io/u/light0-0)\ **Replies:** 5\ **Last updated:** [September 12, 2024, 7:21am UTC](https://community.pinecone.io/t/attributeerror-while-performing-pinecone-from-texts/5239 "2024-09-12T07:21:44Z")
docsearch=PV.from\_texts(\[t.page\_content for t in text\_chunks\], embeddings, index\_name=index\_name) I don’t know why this is showing i tried a lot solving this and yesterday when i was practicing it was perfectly worki… --- ## [Pinecone ERROR Vector dimension 768 does not match the dimension of the index 384](https://community.pinecone.io/t/pinecone-error-vector-dimension-768-does-not-match-the-dimension-of-the-index-384/5815)
**Author:** [@lisboua](https://community.pinecone.io/u/lisboua)\ **Replies:** 1\ **Last updated:** [June 4, 2024, 1:50pm UTC](https://community.pinecone.io/t/pinecone-error-vector-dimension-768-does-not-match-the-dimension-of-the-index-384/5815 "2024-06-04T13:50:48Z")
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 from pymongo import M… --- ## [Problem indexing in pinecone](https://community.pinecone.io/t/problem-indexing-in-pinecone/1820)
**Author:** [@SerSanC](https://community.pinecone.io/u/SerSanC)\ **Replies:** 3\ **Last updated:** [May 13, 2024, 2:28pm UTC](https://community.pinecone.io/t/problem-indexing-in-pinecone/1820 "2024-05-13T14:28:35Z")
Hello, I’m new to Pinecone and I’m trying to index with pinecone with a p1.x1 index (the paid version, not the free one), 500k vectors. The problem arises that when I get to 70-80% this error appears, without any kind o… --- ## [How to convert SQL table into Pinecone and ask question?](https://community.pinecone.io/t/how-to-convert-sql-table-into-pinecone-and-ask-question/4865)
**Author:** [@moongates5000](https://community.pinecone.io/u/moongates5000)\ **Replies:** 1\ **Last updated:** [March 19, 2024, 1:26pm UTC](https://community.pinecone.io/t/how-to-convert-sql-table-into-pinecone-and-ask-question/4865 "2024-03-19T13:26:45Z")
I want to have a SQL table and want to convert it into Pinecone and allow user ask questions. I am gonna using Pinecone and Langchain, OpenAI for this project. My table looks like this : company name, members, annual … --- ## [I am getting this weird Error, does anybody know why this is happening and how to solve it](https://community.pinecone.io/t/i-am-getting-this-weird-error-does-anybody-know-why-this-is-happening-and-how-to-solve-it/3702)
**Author:** [@brayan0404](https://community.pinecone.io/u/brayan0404)\ **Replies:** 2\ **Last updated:** [November 20, 2023, 6:35am UTC](https://community.pinecone.io/t/i-am-getting-this-weird-error-does-anybody-know-why-this-is-happening-and-how-to-solve-it/3702 "2023-11-20T06:35:55Z")
PineconeException: UNKNOWN:Error received from peer ipv4:34.160.88.44:443 {created\_time:“2023-11-18T23:32:44.883513453+00:00”, grpc\_status:3, grpc\_message:“Request size 3MB exceeds the maximum supported size of 2MB”} th… --- ## [Encode\_documents and encode\_queries functions](https://community.pinecone.io/t/encode-documents-and-encode-queries-functions/3628)
**Author:** [@christopher3141](https://community.pinecone.io/u/christopher3141)\ **Replies:** 0\ **Last updated:** [November 7, 2023, 6:18pm UTC](https://community.pinecone.io/t/encode-documents-and-encode-queries-functions/3628 "2023-11-07T18:18:02Z")
why is there both encode\_documents and encode\_queries functions for both sparse and dense encoding of text? is the reason the same for both sparse and dense encoding? I’m looking at here: GitHub - pinecone-io/pinecone-t… --- ## [Best way to deploy using open source huggingface embeddings?](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397)
**Author:** [@burberg92](https://community.pinecone.io/u/burberg92)\ **Replies:** 1\ **Last updated:** [October 14, 2023, 2:35pm UTC](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397 "2023-10-14T14:35:44Z")
In an application where users constantly upload documents, generating embeddings would be one of the biggest cost if using paid embeddings such as openai’s embedding. Using open source embeddings would be free but I am w… --- ## [Invalid vector value passed: cannot interpret type \](https://community.pinecone.io/t/invalid-vector-value-passed-cannot-interpret-type-class-list/2563)
**Author:** [@arman.hn007](https://community.pinecone.io/u/arman.hn007)\ **Replies:** 2\ **Last updated:** [July 6, 2023, 5:03pm UTC](https://community.pinecone.io/t/invalid-vector-value-passed-cannot-interpret-type-class-list/2563 "2023-07-06T17:03:25Z")
from langchain.llms import OpenAI from sentence\_transformers import SentenceTransformer from langchain.embeddings import OpenAIEmbeddings from dotenv import load\_dotenv import os import glob import pdfplumber import pine… --- ## [Sync database and pinecone](https://community.pinecone.io/t/sync-database-and-pinecone/1559)
**Author:** [@ThomasDudu](https://community.pinecone.io/u/ThomasDudu)\ **Replies:** 0\ **Last updated:** [April 27, 2023, 12:01pm UTC](https://community.pinecone.io/t/sync-database-and-pinecone/1559 "2023-04-27T12:01:08Z")
Hey everyone, I was wondering if guys had any tips on how to synchronize your main database and the pinecone database / vector database… For my part, I have a backend in golang, and every time a text is inserted/updated… --- ## [Fine-tune sentence-transformers model using MNR loss](https://community.pinecone.io/t/fine-tune-sentence-transformers-model-using-mnr-loss/408)
**Author:** [@joaocp13](https://community.pinecone.io/u/joaocp13)\ **Replies:** 1\ **Last updated:** [March 15, 2023, 8:27pm UTC](https://community.pinecone.io/t/fine-tune-sentence-transformers-model-using-mnr-loss/408 "2023-03-15T20:27:34Z")
Hello, I’m a student working on a thesis about neural retrieval and I saw Pinecone’s article about the MNR loss. I’m trying to fine-tune a sentence-transformer model using the MNR loss but I’m having some troubles imple… --- ## [Sentence-transformer or DPR?](https://community.pinecone.io/t/sentence-transformer-or-dpr/299)
**Author:** [@sophiem](https://community.pinecone.io/u/sophiem)\ **Replies:** 0\ **Last updated:** [March 11, 2022, 7:14pm UTC](https://community.pinecone.io/t/sentence-transformer-or-dpr/299 "2022-03-11T19:14:13Z")
Not sure when to use sentence-transformer or dense passage retrieval? Our friends over at SBERT can help you out. Take a look here. --- ## [Sentence transformers for keyword clustering for SEO](https://community.pinecone.io/t/sentence-transformers-for-keyword-clustering-for-seo/231)
**Author:** [@sophiem](https://community.pinecone.io/u/sophiem)\ **Replies:** 0\ **Last updated:** [February 18, 2022, 2:40pm UTC](https://community.pinecone.io/t/sentence-transformers-for-keyword-clustering-for-seo/231 "2022-02-18T14:40:44Z")
Interesting article reshared by Nils Reimers from Search Engine Journal on how to semantically cluster keywords in bulk with multilingual support. --- ## [Sentence coverage](https://community.pinecone.io/t/sentence-coverage/211)
**Author:** [@Laura](https://community.pinecone.io/u/Laura)\ **Replies:** 1\ **Last updated:** [February 8, 2022, 2:29pm UTC](https://community.pinecone.io/t/sentence-coverage/211 "2022-02-08T14:29:47Z")
Is it possible to use SBERT models to understand the extent of coverage of a query sentence across the whole document? For example, if a query sentence consists of ‘X and Y’ and one sentence in the document refers to ‘X’… --- ## [Bi-encoder and cross-encoder](https://community.pinecone.io/t/bi-encoder-and-cross-encoder/209)
**Author:** [@Laura](https://community.pinecone.io/u/Laura)\ **Replies:** 1\ **Last updated:** [February 8, 2022, 2:13pm UTC](https://community.pinecone.io/t/bi-encoder-and-cross-encoder/209 "2022-02-08T14:13:59Z")
I’m currently working on a project to identify most similar sentences in a document to a specified query sentence. I’m using a pre-trained SBERT bi-encoder model for this but have just started looking at using a cross-en… --- ## [Is it necessary to fine-tune the \*BERT base models from HuggingFace before being able to use the pooled output to perform similarity search?](https://community.pinecone.io/t/is-it-necessary-to-fine-tune-the-bert-base-models-from-huggingface-before-being-able-to-use-the-pooled-output-to-perform-similarity-search/198)
**Author:** [@rdisipio](https://community.pinecone.io/u/rdisipio)\ **Replies:** 1\ **Last updated:** [February 7, 2022, 7:45pm UTC](https://community.pinecone.io/t/is-it-necessary-to-fine-tune-the-bert-base-models-from-huggingface-before-being-able-to-use-the-pooled-output-to-perform-similarity-search/198 "2022-02-07T19:45:57Z")
Hi, is it necessary to fine-tune the \*BERT base models from HuggingFace before being able to use the pooled output to perform similarity search? Or would they work out-of-the box? Cheers, Riccardo --- ## [Sentence Similarity Search](https://community.pinecone.io/t/sentence-similarity-search/163)
**Author:** [@skcary](https://community.pinecone.io/u/skcary)\ **Replies:** 1\ **Last updated:** [February 3, 2022, 7:47pm UTC](https://community.pinecone.io/t/sentence-similarity-search/163 "2022-02-03T19:47:01Z")
I would like to have the ability to type in a sentence (or perhaps a few sentences), and return the sentences from my content that are most similar. I have looked at the tutorial on semantic search here: Semantic textua… --- ## [Training Sentence Transformers](https://community.pinecone.io/t/training-sentence-transformers/39)
**Author:** [@jamesbriggs](https://community.pinecone.io/u/jamesbriggs)\ **Replies:** 4\ **Last updated:** [January 27, 2022, 3:40am UTC](https://community.pinecone.io/t/training-sentence-transformers/39 "2022-01-27T03:40:29Z")
q1) In the course Unsupervised Training for Sentence Transformers | Pinecone you have explained 3 training methods - Training Sentence Transformers with Softmax Loss , Training Sentence Transformers with MNR Loss and …