Comments (3)
π€
Hi @troublesprouter! It's great to see you again. I hope all has been going well since our last interaction.
Based on the information provided, the Pinecone integration is implemented in the utils/pinecone-client.ts
file. However, the specific function responsible for querying the Pinecone database and setting the number of results returned by a Pinecone query is not specified in the provided context.
Typically, in Pinecone, the number of results returned by a query can be controlled by a parameter called top_k
in the query function. This parameter specifies the number of nearest neighbors to return.
If this is the case in the gpt4-pdf-chatbot-langchain
repository, you should be able to modify the top_k
parameter in the query function in the utils/pinecone-client.ts
file to control the number of results returned.
However, without the specific function or the implementation details, I can't provide a more accurate answer. Could you please provide more details about the function or the implementation of the Pinecone query in the utils/pinecone-client.ts
file? This will help me give you a more precise answer.
For more information about Pinecone's query function and the top_k
parameter, you can refer to the Pinecone documentation.
I hope this helps! If you have any more questions, feel free to ask.
Sources
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a π if this is helpful and π if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
from gpt4-pdf-chatbot-langchain.
π€
Hi, @troublesprouter
I'm helping the gpt4-pdf-chatbot-langchain team manage their backlog and am marking this issue as stale. It seems that you have already resolved the issue by adding a line of code in the chat.ts
file to set the number of results to be returned.
Could you please confirm if this issue is still relevant to the latest version of the gpt4-pdf-chatbot-langchain repository? If it is, kindly let the gpt4-pdf-chatbot-langchain team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!
from gpt4-pdf-chatbot-langchain.
Found the solution:
On line 57 of chat.ts, add:
// Set the number of results to be returned
retriever.k = 10; // Replace 10 with your desired number of results
so that it now looks like this:
// Use a callback to get intermediate sources from the middle of the chain
let resolveWithDocuments: (value: Document[]) => void;
const documentPromise = new Promise<Document[]>((resolve) => {
resolveWithDocuments = resolve;
});
const retriever = vectorStore.asRetriever({
callbacks: [
{
handleRetrieverEnd(documents) {
resolveWithDocuments(documents);
},
},
],
});
// Set the number of results to be returned
retriever.k = 10; // Replace 10 with your desired number of results
//create chain
const chain = makeChain(retriever);
from gpt4-pdf-chatbot-langchain.
Related Issues (20)
- how do i ssl? HOT 3
- Conversion of code into Python HOT 2
- PineconeError: Error, message length too large: found 5453452 bytes, the limit is: 4194304 bytes HOT 6
- source output HOT 1
- How to change the BaseUrl if I use a proxy HOT 1
- Can ChatGPT 3.5 be supportedοΌ HOT 6
- Text words overlay display HOT 1
- Does this project accepts image read from PDF? HOT 5
- Enhancement - ability to use a graph database such as neo4j instead of vector database HOT 1
- enhancement - integrate with llamaindex HOT 3
- Explain data ingestion code. HOT 4
- s HOT 1
- "TypeError: Cannot read properties of undefined (reading 'text')" HOT 1
- error TypeError: ids is not iterable HOT 1
- Add support for Pinecone Serverless HOT 7
- Error: Azure OpenAI API instance name not found HOT 3
- FetchError: request to https://api.openai.com/v1/embeddings failed HOT 1
- run "yarn run ingest" Japanese punctuation marks were converted to Korean HOT 1
- I get this error when I open my local server: Cannot read properties of undefined (reading 'text') HOT 14
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gpt4-pdf-chatbot-langchain.