# Why Pinecone vector db result is not perfect for retrieval on complex query?

**URL:** <https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925>\
**Category:** Support\
**Tags:** semantic-search\
**Created:** [December 29, 2023, 11:18am UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925 "2023-12-29T11:18:08Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![ai1](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/ai1/32/4385_2.png) [@ai1](https://community.pinecone.io/u/ai1)\
**Post date:** [December 29, 2023, 11:18am UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925/1 "2023-12-29T11:18:08Z")

</div>

Hi, I’ve embedded the Wikipedia pages of 50 United States presidents using a Hugging Face model and stored those embeddings on Pinecone. I asked a simple question: ‘Please provide me with the name of the college that most U.S. presidents attended, and also give me a list of those presidents.’ However, it’s giving me the right similar vector embeddings. Can anybody help me with how to solve this type of problem?

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex020/uploads/pinecone/original/1X/d16664eba369eeee623700cf12feab5562b37eaf.jpeg) [@system](https://community.pinecone.io/u/system)\
**Post date:** [January 12, 2024, 11:18am UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925/2 "2024-01-12T11:18:55Z")

</div>

Closed on January 12, 2024, 11:18am UTC

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.

---

<div class="post-metadata">

**Author:** ![Cory\_Pinecone](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/cory_pinecone/32/1712_2.png) [@Cory\_Pinecone](https://community.pinecone.io/u/Cory_Pinecone)\
**Post date:** [January 17, 2024, 4:22pm UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925/3 "2024-01-17T16:22:47Z")

</div>

@ai1 I’m not sure I understand the issue. When you say it’s giving you the right similar vector embeddings, do you mean you’re getting the results you expect?

Can you give an example of the queries you’re running, the results you expect to get, and the results you’re actually getting?

---

<div class="post-metadata">

**Author:** ![jocelyn](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/jocelyn/32/1653_2.png) [@jocelyn](https://community.pinecone.io/u/jocelyn)\
**Post date:** [January 17, 2024, 6:23pm UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925/4 "2024-01-17T18:23:01Z")

</div>

Opened on January 17, 2024, 6:23pm UTC



---

<div class="post-metadata">

**Author:** ![jocelyn](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/jocelyn/32/1653_2.png) [@jocelyn](https://community.pinecone.io/u/jocelyn)\
**Post date:** [January 17, 2024, 6:23pm UTC](https://community.pinecone.io/t/why-pinecone-vector-db-result-is-not-perfect-for-retrieval-on-complex-query/3925/5 "2024-01-17T18:23:09Z")

</div>

Closed on January 17, 2024, 6:23pm UTC