# \#embeddings **URL:** https://community.pinecone.io/tag/embeddings/41.md [Latest](https://community.pinecone.io/latest.md) · [Categories](https://community.pinecone.io/categories.md) · [Tags](https://community.pinecone.io/tags.md) --- ## [Can I use text-embedding-3-large model with 1536 dimension in Pinecone?](https://community.pinecone.io/t/can-i-use-text-embedding-3-large-model-with-1536-dimension-in-pinecone/8432)
**Author:** [@trevor.dev23](https://community.pinecone.io/u/trevor.dev23)\ **Replies:** 4\ **Last updated:** [October 23, 2025, 1:09am UTC](https://community.pinecone.io/t/can-i-use-text-embedding-3-large-model-with-1536-dimension-in-pinecone/8432 "2025-10-23T01:09:50Z")
Hi everyone :waving\_hand: I’ve been experimenting with the OpenAI text-embedding-3-large model through the API, and interestingly, it’s returning 1536-dimensional embeddings for my text inputs — and they work great so f… --- ## [Join Pinecone Office Hours, this Friday on Zoom](https://community.pinecone.io/t/join-pinecone-office-hours-this-friday-on-zoom/8431)
**Author:** [@jocelyn](https://community.pinecone.io/u/jocelyn)\ **Replies:** 0\ **Last updated:** [October 21, 2025, 7:23pm UTC](https://community.pinecone.io/t/join-pinecone-office-hours-this-friday-on-zoom/8431 "2025-10-21T19:23:02Z")
What are you up to this Friday? Don’t miss Pinecone Office Hours on Zoom! Deets below :backhand\_index\_pointing\_down: → Register: Webinar Registration - Zoom Have questions or need help launching your projects? Drop … --- ## [Failed to upload PDF file in Pinecone Assistant](https://community.pinecone.io/t/failed-to-upload-pdf-file-in-pinecone-assistant/8412)
**Author:** [@nerstuff24](https://community.pinecone.io/u/nerstuff24)\ **Replies:** 1\ **Last updated:** [October 13, 2025, 11:37pm UTC](https://community.pinecone.io/t/failed-to-upload-pdf-file-in-pinecone-assistant/8412 "2025-10-13T23:37:18Z")
Hello community, I’m new here. I want to ask about uploading my PDF file. Why does it keep failing? My PDF has been compressed to 3 MB. Can anyone help? Thank you. --- ## [What's the recommended approach for implementing TTL functionality in Pinecone?](https://community.pinecone.io/t/whats-the-recommended-approach-for-implementing-ttl-functionality-in-pinecone/8385)
**Author:** [@dadepetun](https://community.pinecone.io/u/dadepetun)\ **Replies:** 0\ **Last updated:** [September 12, 2025, 1:01pm UTC](https://community.pinecone.io/t/whats-the-recommended-approach-for-implementing-ttl-functionality-in-pinecone/8385 "2025-09-12T13:01:18Z")
(topic deleted by author) --- ## [Using Pinecone for NLP-to-SQL RAG – Is it a good fit?](https://community.pinecone.io/t/using-pinecone-for-nlp-to-sql-rag-is-it-a-good-fit/8367)
**Author:** [@harinathharinath79](https://community.pinecone.io/u/harinathharinath79)\ **Replies:** 0\ **Last updated:** [August 22, 2025, 5:16am UTC](https://community.pinecone.io/t/using-pinecone-for-nlp-to-sql-rag-is-it-a-good-fit/8367 "2025-08-22T05:16:02Z")
Hi everyone, I’m working on an NLP-to-SQL RAG (Retrieval-Augmented Generation) project and I’m wondering if Pinecone is a good fit for this use case. Could someone explain the pros and cons of using Pinecone for these t… --- ## [Incident on us-east-1 environment ? Suddenly cant fetch embeddings](https://community.pinecone.io/t/incident-on-us-east-1-environment-suddenly-cant-fetch-embeddings/8311)
**Author:** [@jmcelhiney619](https://community.pinecone.io/u/jmcelhiney619)\ **Replies:** 2\ **Last updated:** [August 13, 2025, 4:11pm UTC](https://community.pinecone.io/t/incident-on-us-east-1-environment-suddenly-cant-fetch-embeddings/8311 "2025-08-13T16:11:56Z")
Didnt make any changes, same API key and index being used but all of a sudden stopped working. Pinecone returns 200 OK, but provides no response body, application hasn’t worked now for about an hour+ . Any current issue … --- ## [Search similarity use case which integrated embedding model offered by Pinecone is best for the scenario?](https://community.pinecone.io/t/search-similarity-use-case-which-integrated-embedding-model-offered-by-pinecone-is-best-for-the-scenario/8299)
**Author:** [@s.thirugna](https://community.pinecone.io/u/s.thirugna)\ **Replies:** 2\ **Last updated:** [August 1, 2025, 9:27pm UTC](https://community.pinecone.io/t/search-similarity-use-case-which-integrated-embedding-model-offered-by-pinecone-is-best-for-the-scenario/8299 "2025-08-01T21:27:22Z")
I’m building an application that relies on high-quality semantic search to retrieve relevant messages and conversations. My goal is to deliver fast, accurate, and contextually aware search results for user queries typed … --- ## [Issue: Incorrect context being fetched in Docker environment despite correct namespace](https://community.pinecone.io/t/issue-incorrect-context-being-fetched-in-docker-environment-despite-correct-namespace/8284)
**Author:** [@tushar.ekad](https://community.pinecone.io/u/tushar.ekad)\ **Replies:** 5\ **Last updated:** [July 29, 2025, 5:17pm UTC](https://community.pinecone.io/t/issue-incorrect-context-being-fetched-in-docker-environment-despite-correct-namespace/8284 "2025-07-29T17:17:51Z")
Hi everyone, I’m facing a strange issue with my Pinecone integration. The app works perfectly when run locally — it fetches the correct context from the specified namespace. However, when I run the exact same setup insi… --- ## [ChatGPT GPT embedding + querying schema](https://community.pinecone.io/t/chatgpt-gpt-embedding-querying-schema/8234)
**Author:** [@connor](https://community.pinecone.io/u/connor)\ **Replies:** 2\ **Last updated:** [July 16, 2025, 4:24pm UTC](https://community.pinecone.io/t/chatgpt-gpt-embedding-querying-schema/8234 "2025-07-16T16:24:51Z")
Hello folks, I’m trying to use Pinecone to supply additional context to queries made in ChatGPT, via OpenAI’s “GPTs” tool. I have a Pinecone index using llama-text-embed-v2 (with integrated embedding) to store contextu… --- ## [PineconeApiException: (422) Reason: Unprocessable Entity](https://community.pinecone.io/t/pineconeapiexception-422-reason-unprocessable-entity/8196)
**Author:** [@szymskul](https://community.pinecone.io/u/szymskul)\ **Replies:** 4\ **Last updated:** [July 2, 2025, 9:32pm UTC](https://community.pinecone.io/t/pineconeapiexception-422-reason-unprocessable-entity/8196 "2025-07-02T21:32:57Z")
Hi, I am trying to create sparse index on local Pinecone Local development with Pinecone Local - Pinecone Docs, but when I compile this lines sparse\_index\_name = "sparse-index" if not pc.has\_index(sparse\_index\_name): … --- ## [Execution time for inserting PDF documents into Pinecone in an n8n workflow](https://community.pinecone.io/t/execution-time-for-inserting-pdf-documents-into-pinecone-in-an-n8n-workflow/8185)
**Author:** [@visions2060](https://community.pinecone.io/u/visions2060)\ **Replies:** 2\ **Last updated:** [July 1, 2025, 4:37pm UTC](https://community.pinecone.io/t/execution-time-for-inserting-pdf-documents-into-pinecone-in-an-n8n-workflow/8185 "2025-07-01T16:37:06Z")
I created an n8n workflow where I perform RAG. Documents located in a OneDrive folder are injected into Pinecone for vectorization. It turns out that, regardless of the document size or number of files, the Pinecone node… --- ## [Error uploading embeddings for a 1.5mb file](https://community.pinecone.io/t/error-uploading-embeddings-for-a-1-5mb-file/7400)
**Author:** [@martin1](https://community.pinecone.io/u/martin1)\ **Replies:** 4\ **Last updated:** [May 22, 2025, 2:31pm UTC](https://community.pinecone.io/t/error-uploading-embeddings-for-a-1-5mb-file/7400 "2025-05-22T14:31:44Z")
Hi, I’m trying to upload the embeddings generated with a text-small openai embeddings model of the attached file but it fails with the following message: {“code”=\>11, “message”=\>“Error, message length too large: found … --- ## [ValueError when initializing PineconeVectorStore with LangChain](https://community.pinecone.io/t/valueerror-when-initializing-pineconevectorstore-with-langchain/7538)
**Author:** [@alejogbravo](https://community.pinecone.io/u/alejogbravo)\ **Replies:** 5\ **Last updated:** [May 20, 2025, 8:10pm UTC](https://community.pinecone.io/t/valueerror-when-initializing-pineconevectorstore-with-langchain/7538 "2025-05-20T20:10:04Z")
Title: ValueError with langchain\_community.vectorstores Pinecone Integration Hi everyone, I’m getting this error when trying to initialize a Pinecone vector store using the community package: ValueError: client should… --- ## [Dimensions of the embeddings using the embedding model: llama-text-embed-2 hosted by pinecone are not changing](https://community.pinecone.io/t/dimensions-of-the-embeddings-using-the-embedding-model-llama-text-embed-2-hosted-by-pinecone-are-not-changing/7886)
**Author:** [@ahmedosamaizhar21](https://community.pinecone.io/u/ahmedosamaizhar21)\ **Replies:** 1\ **Last updated:** [April 23, 2025, 3:50pm UTC](https://community.pinecone.io/t/dimensions-of-the-embeddings-using-the-embedding-model-llama-text-embed-2-hosted-by-pinecone-are-not-changing/7886 "2025-04-23T15:50:34Z")
def get\_embedding(texts): “”" Get embeddings for a list of texts “”" embeddings = pc.inference.embed( model=“llama-text-embed-v2”, inputs=texts, parameters={ “input\_type”: “passage”, “dimension”: 2048 } ) ret… --- ## [Accumulation of threads and increased RAM usage over time while embedding](https://community.pinecone.io/t/accumulation-of-threads-and-increased-ram-usage-over-time-while-embedding/7854)
**Author:** [@mhachemi](https://community.pinecone.io/u/mhachemi)\ **Replies:** 2\ **Last updated:** [April 21, 2025, 7:26pm UTC](https://community.pinecone.io/t/accumulation-of-threads-and-increased-ram-usage-over-time-while-embedding/7854 "2025-04-21T19:26:58Z")
Hi everyone, I have a question regarding threads while embedding data into Pinecone. When I call the add\_documents method, I notice that seven new threads are spawned, which seems expected. However, after the operation c… --- ## [No Result when it comes to numeric data](https://community.pinecone.io/t/no-result-when-it-comes-to-numeric-data/7858)
**Author:** [@manjot14122002](https://community.pinecone.io/u/manjot14122002)\ **Replies:** 1\ **Last updated:** [April 17, 2025, 6:42pm UTC](https://community.pinecone.io/t/no-result-when-it-comes-to-numeric-data/7858 "2025-04-17T18:42:29Z")
User Query : tell me about order number 10779 I have used index.query , index.query\_namespaces with all the metric (“cosine”, “euclidean”, “dotproduct”) but did not get any chunks related to order number 10779 . chunks… --- ## [Pinecone Vector Upsert Implementation in Unity - Getting NotFound Error](https://community.pinecone.io/t/pinecone-vector-upsert-implementation-in-unity-getting-notfound-error/7806)
**Author:** [@d34662563](https://community.pinecone.io/u/d34662563)\ **Replies:** 2\ **Last updated:** [April 7, 2025, 10:48pm UTC](https://community.pinecone.io/t/pinecone-vector-upsert-implementation-in-unity-getting-notfound-error/7806 "2025-04-07T22:48:35Z")
Hi everyone, I’m working on implementing Pinecone’s vector upsert functionality into my Unity project, but I’m encountering an issue. When I try to send an upsert request to Pinecone, I receive a NotFound response statu… --- ## [Inconsistent metadata filtering with serverless index](https://community.pinecone.io/t/inconsistent-metadata-filtering-with-serverless-index/7781)
**Author:** [@doriro](https://community.pinecone.io/u/doriro)\ **Replies:** 0\ **Last updated:** [April 2, 2025, 1:31pm UTC](https://community.pinecone.io/t/inconsistent-metadata-filtering-with-serverless-index/7781 "2025-04-02T13:31:21Z")
We currently have a serverless index with the following index stats: ‘dimension’: 768, single namespace, ‘total\_vector\_count’: 2096563 When running this query: response = self.index.query( … --- ## [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… --- ## [High Latency On llama-text-embed-v2](https://community.pinecone.io/t/high-latency-on-llama-text-embed-v2/7697)
**Author:** [@semih](https://community.pinecone.io/u/semih)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 7:40pm UTC](https://community.pinecone.io/t/high-latency-on-llama-text-embed-v2/7697 "2025-03-17T19:40:54Z")
I am having 2.5 seconds (median) latency on embedding creation. Is there an incident or something? anyone having same problem? --- ## [I want to use Pinecone to generate personalised recommendations](https://community.pinecone.io/t/i-want-to-use-pinecone-to-generate-personalised-recommendations/7608)
**Author:** [@mike2](https://community.pinecone.io/u/mike2)\ **Replies:** 0\ **Last updated:** [February 25, 2025, 6:46pm UTC](https://community.pinecone.io/t/i-want-to-use-pinecone-to-generate-personalised-recommendations/7608 "2025-02-25T18:46:34Z")
I am assessing if Pinecone can be used in the following use case: We have businesses in various categories that have various promotions running. We have an app that lists the businesses, ibn categories, and also lists … --- ## [How can i change the dimensions of the embeddings using the embedding model: llama-text-embed-2 hosted by pinecone](https://community.pinecone.io/t/how-can-i-change-the-dimensions-of-the-embeddings-using-the-embedding-model-llama-text-embed-2-hosted-by-pinecone/7581)
**Author:** [@jay.pce21](https://community.pinecone.io/u/jay.pce21)\ **Replies:** 2\ **Last updated:** [February 21, 2025, 5:56pm UTC](https://community.pinecone.io/t/how-can-i-change-the-dimensions-of-the-embeddings-using-the-embedding-model-llama-text-embed-2-hosted-by-pinecone/7581 "2025-02-21T17:56:11Z")
this is my function and when i pass the dimension in parameters as 2048 it still create embedding of 1024, in docs i cant see where to pass dimension parameter, so i have kept it in parameters async def embeddings(input… --- ## [Inconsistent metadata filtering with pod index](https://community.pinecone.io/t/inconsistent-metadata-filtering-with-pod-index/7547)
**Author:** [@rvivas](https://community.pinecone.io/u/rvivas)\ **Replies:** 1\ **Last updated:** [February 17, 2025, 7:37pm UTC](https://community.pinecone.io/t/inconsistent-metadata-filtering-with-pod-index/7547 "2025-02-17T19:37:34Z")
We currently have a pod-based index with the following index stats: {'dimension': 1536, 'index\_fullness': 0.0, 'namespaces': {'': {'vector\_count': 2109}}, 'total\_vector\_count': 2109} When running this query: result… --- ## [PineconeConfigurationError: You haven't specified an Api-Key](https://community.pinecone.io/t/pineconeconfigurationerror-you-havent-specified-an-api-key/5044)
**Author:** [@home.rajnishadhikari](https://community.pinecone.io/u/home.rajnishadhikari)\ **Replies:** 14\ **Last updated:** [February 14, 2025, 9:00am UTC](https://community.pinecone.io/t/pineconeconfigurationerror-you-havent-specified-an-api-key/5044 "2025-02-14T09:00:42Z")
For this code docsearch = Pinecone.from\_texts(\[t.page\_content for t in text\_chunks\], embedding, index\_name="testforpractical") I got below error PineconeConfigurationError: You haven't specified an Api-Key. and i tri… --- ## [My PDF RAG app isn't able to return correct documents for a query , what may be the reason?](https://community.pinecone.io/t/my-pdf-rag-app-isnt-able-to-return-correct-documents-for-a-query-what-may-be-the-reason/7505)
**Author:** [@gauravmindzk](https://community.pinecone.io/u/gauravmindzk)\ **Replies:** 1\ **Last updated:** [February 11, 2025, 7:02am UTC](https://community.pinecone.io/t/my-pdf-rag-app-isnt-able-to-return-correct-documents-for-a-query-what-may-be-the-reason/7505 "2025-02-11T07:02:10Z")
Hello everyone, I’m currently developing a PDF RAG app and running into a problem . Let’s understand my app workflow. A user uploads a PDF , clicks to ‘Process’ it. I’ve used pymupdf4llm as the pdf parser. It effecti… --- ## [Need help with Embeddings - TypeError: records.forEach is not a function](https://community.pinecone.io/t/need-help-with-embeddings-typeerror-records-foreach-is-not-a-function/6526)
**Author:** [@nnettey](https://community.pinecone.io/u/nnettey)\ **Replies:** 11\ **Last updated:** [February 10, 2025, 6:37am UTC](https://community.pinecone.io/t/need-help-with-embeddings-typeerror-records-foreach-is-not-a-function/6526 "2025-02-10T06:37:13Z")
I could use some help here, I’m using the following versions: NodeJS (v20.11.0) @pinecone-database/pinecone": “^3.0.2” OpenAI model text-embedding-ada-002 Error: Error during embedding generation: TypeError: records.… --- ## [Error upserting docs to pinecone](https://community.pinecone.io/t/error-upserting-docs-to-pinecone/7206)
**Author:** [@hello4](https://community.pinecone.io/u/hello4)\ **Replies:** 2\ **Last updated:** [February 7, 2025, 12:23pm UTC](https://community.pinecone.io/t/error-upserting-docs-to-pinecone/7206 "2025-02-07T12:23:26Z")
Hi, I am getting an error while uploading data to Pinecone. Error message: Error upserting to Pinecone: TypeError: records.forEach is not a function. This is what the metadataList looks like: \[ { id: 'Using pin… --- ## [Recommended models](https://community.pinecone.io/t/recommended-models/7427)
**Author:** [@chandini.paterson](https://community.pinecone.io/u/chandini.paterson)\ **Replies:** 0\ **Last updated:** [January 27, 2025, 10:56am UTC](https://community.pinecone.io/t/recommended-models/7427 "2025-01-27T10:56:23Z")
Hello, Is there a recommendation around the embeddings or LLM models to use with Pinecone, in order to keep costs low? I have just started playing around with Pinecode Assistant and finding it useful. But I’m using th… --- ## [What is the best Arabic embedding and tokenization models?](https://community.pinecone.io/t/what-is-the-best-arabic-embedding-and-tokenization-models/5427)
**Author:** [@obadarneh99](https://community.pinecone.io/u/obadarneh99)\ **Replies:** 5\ **Last updated:** [January 20, 2025, 6:32pm UTC](https://community.pinecone.io/t/what-is-the-best-arabic-embedding-and-tokenization-models/5427 "2025-01-20T18:32:08Z")
Dears, What is the best embedding model for Arabic Data sets, as the current answers that I get from my “chat with your website” LLM application are not correct? I am using currently 1- “text-embedding-ada-002” as emb… --- ## [Sparse Vectors with Golang?](https://community.pinecone.io/t/sparse-vectors-with-golang/7212)
**Author:** [@brandon](https://community.pinecone.io/u/brandon)\ **Replies:** 2\ **Last updated:** [January 8, 2025, 1:08am UTC](https://community.pinecone.io/t/sparse-vectors-with-golang/7212 "2025-01-08T01:08:54Z")
Hi there, I’ve been digging through the Golang SDK and cannot find a way to generate Sparse Vectors. There is a struct representation that is used in the Vector struct, but no way to use the Inference Client to generate … [Next page](https://community.pinecone.io/tag/embeddings/41.md?match_all_tags=true&page=1&tags%5B%5D=embeddings)