GithubHelp home page GithubHelp logo

pinecone-io / semantic-search-example Goto Github PK

View Code? Open in Web Editor NEW
56.0 56.0 20.0 5.14 MB

A TypeScript demo app using the Pinecone vector database

Home Page: https://www.pinecone.io

TypeScript 100.00%

semantic-search-example's People

Contributors

austin-denoble avatar dejanmiletic89 avatar jhamon avatar rschwabco avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

semantic-search-example's Issues

[Feature] OpenAI embeddings

Is this your first time submitting a feature request?

  • I have searched the existing issues, and I could not find an existing issue for this feature
  • I am requesting a straightforward extension of existing functionality

Describe the feature

Hello! I appreciate your efforts in creating this.

May I inquire if it's feasible to incorporate OpenAI embeddings? If it is, how challenging would it be to integrate both the current and OpenAI embeddings in this script?

If you can direct me on how to do it, I would gladly assist in adding that feature. I am unfamiliar with Pinecone, so any assistance would be beneficial. Thank you!

Describe alternatives you've considered

No response

Who will this benefit?

No response

Are you interested in contributing this feature?

No response

Anything else?

No response

[Bug] Cannot upsert second column of questions with current behavior of load.ts

Is this a new bug?

  • I believe this is a new bug
  • I have searched the existing issues, and I could not find an existing issue for this bug

Current Behavior

When I run npm start -- load --csvPath=test.csv --column=question2, I get the following error:

PineconeUnmappedHttpError: An unexpected error occured while calling the https://controller.us-east4-gcp.pinecone.io/databases endpoint.  index semantic-search already exists Status: 409.

After discussion with Roie, there should be a simple fix in load.ts that can properly check for the existence of the index and properly connect to the existing index to allow for the upload of the second column.

Expected Behavior

The npm start -- load --csvPath=test.csv --column=question2 command in the ReadMe executes without issue and the second column of questions is uploaded.

Steps To Reproduce

  1. Clone the repository and execute npm run build.
  2. Run npm start -- load --csvPath=test.csv --column=question1
  3. Run npm start -- load --csvPath=test.csv --column=question2 and observe the error noted above.

Relevant log output

No response

Environment

- **OS**:
- **Language version**:
- **Pinecone client version**:

Additional Context

No response

[Bug] Missing `metric` parameter in `pinecone.createIndex`

Is this a new bug?

  • I believe this is a new bug
  • I have searched the existing issues, and I could not find an existing issue for this bug

Current Behavior

The application throws a runtime error when trying to load the column question1 into the index semantic-search

See: src/load.ts, missing parameter metric

Expected Behavior

The application should load the column question1 into the index semantic-search

Steps To Reproduce

Follow the instructions in README.md:

  1. build the application
  2. run npm start -- load --csvPath=test.csv --column=question1

Relevant log output

PineconeUnmappedHttpError: An unexpected error occured while calling the https://controller.gcp-starter.pinecone.io/databases endpoint.  Failed to deserialize the JSON body into the target type: missing field `metric` at line 1 column 42 Status: 422.

Environment

  • OS: macOS Ventura 13.6
  • Language version: typescript
  • Pinecone client version: ^1.0.0

Additional Context

No response

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.