146 questions
Advice
1
vote
1
replies
20
views
RAG with Pinecone + GPT-5 for generating new math problems: incoherent outputs, mixed chunks, and lack of originality
I’m building a tool that generates new mathematics exam problems using an internal database of past problems.
My current setup uses a RAG pipeline, Pinecone as the vector database, and GPT-5 as the ...
Best practices
0
votes
1
replies
105
views
Regarding rag for telephony with deepgram
I'm building a voice-based calling system where users can create AI agents that make outbound phone calls.
The agent uses Deepgram for real-time transcription and ElevenLabs/Cartesia for speech ...
Advice
0
votes
1
replies
58
views
How can I group transcribed phrases into meaningful chunks without using complex models?
I have a large set of phrases obtained via Azure Fast Transcription, and I need to group them into coherent semantic chunks (to use later in a RAG pipeline).
Initially, I tried grouping phrases based ...
- 13
0
votes
0
answers
54
views
Langchain RAG is not retrieving any document
This is my embedding code, which I run once only:
embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
vector_store = MongoDBAtlasVectorSearch.from_connection_string(
...
- 161
0
votes
0
answers
24
views
How to exclude metadata from embedding?
I'm using LlamaIndex 0.14.7. I would like to embed document text without concatenating metadata, because I put a long text in metadata. Here's my code:
table_vec_store: SimpleVectorStore = ...
- 421
1
vote
1
answer
122
views
Why does answer_relevancy return NaN when evaluating RAG with Ragas?
I’m trying to evaluate my Retrieval-Augmented Generation (RAG) pipeline using Ragas.
.
Here’s a complete version of my code:
"""# RAG Evaluation"""
from datasets import ...
- 11
1
vote
0
answers
51
views
Why does my LangChain RAG chatbot sometimes miss relevant chunks in semantic search?
I built a RAG chatbot using LangChain + ChromaDB + OpenAI embeddings. The pipeline works, but sometimes the chatbot doesn’t return the most relevant PDF content, even though it exists in the vector DB....
0
votes
0
answers
146
views
Zep Graphiti - core - Adding Episode fails the LLM structured output
On the ingestion part to the graph db, I pass a json file, as an episode, custom entities (and edges), using gemini api, but I get some discrepancy on the structured output, like so:
LLM generation ...
0
votes
1
answer
64
views
Chroma not accepting lists in persistentClient collection?
My objective is to do keyword filtering in Chroma. I have a field called keywords with a list of strings and I want to filter with it, but chroma won't let me add lists as a field.
I checked my Chroma ...
1
vote
0
answers
72
views
RAG Chatbot does not answer paraphrased questions
I built a RAG chatbot in python,langchain, and FAISS for the vectorstore.
And the data is stored as JSON.
The chatbot sometimes refuses to answer when a question is rephrased.
Here are two ...
0
votes
1
answer
55
views
module not found in haystack 2.17.1
i am trying to create a small starter llm RAG project using haystack. my project packages are below (I use UV):
[project]
name = "llm-project"
version = "0.1.0"
description = "...
- 984
1
vote
0
answers
71
views
ragas with Ollama does not terminate
I am using the python package ragas with the goal of generating a testset for a RAG application.
I am defining my BaseRagasLLM as:
from langchain_ollama import OllamaLLM
from ragas.llms import ...
- 21
0
votes
0
answers
131
views
How to Use Pytest Fixtures in a RAG-Based LangChain Streamlit App?
I'm building a RAG (Retrieval-Augmented Generation) chatbot using LangChain, Gemini API, and Qdrant, with a Streamlit frontend. I want to write unit tests for the app using pytest, and I’m trying to ...
0
votes
0
answers
75
views
How to accelerate my corpus embedding to the chromadb
I have the corpus.jsonl which has 6.5gb storage.And i use the one h100 gpu to embedding the corpus to the chromadb,but it seems very slowly.I want to find how can i accelerate the progress(gpu,cpu,io)....
- 23
0
votes
1
answer
120
views
How do I prevent duplicate messages in context window, when using rag and memory?
When using rag and memory, multiple identical copies of the same information is sent to the ai, when asking related questions.
I have
import java.util.ArrayList;
import java.util.List;
import dev....
- 5,535
1
vote
1
answer
260
views
Firecrawl self-hosted crawler throws Connection violated security rules error
I set up a self-hosted Firecrawl instance and I want to crawl my internal intranet site (e.g. https://intranet.xxx.gov.tr/).
I can access the site directly both from the host machine and from inside ...
- 307
0
votes
0
answers
56
views
How to send extra headers from RAGFlow Agent to a Spring Boot MCP server tool call?
I am using RAGFlow
connected to a Spring Boot MCP server.
My agent flow is simple:
Begin node → collects inputs (auth_token, tenant_id, x_request_status)
Agent (gpt-4o) → connected to
MCP Tool (server)...
- 729
2
votes
1
answer
186
views
Why is FAISS document retrieval slow and inconsistent on EC2 t3.micro instance?
I'm building a document Q&A system using FAISS for vector search on an AWS EC2 t3.micro instance (1 vCPU, 1GB RAM). My FAISS index is relatively small (8.4MB .faiss + 1.4MB .pkl files), but I'm ...
- 65
-1
votes
1
answer
54
views
How to ensure all documents contribute to summary context after merging indexes?
I'm building a LangChain RAG pipeline using the FAISS vector store. I'm merging multiple FAISS indexes — each representing one document — and then querying them to generate summaries or answers via ...
- 54
-4
votes
1
answer
143
views
I want to know where to locate the file I upload though the ragflow system, how to find it in the windows system
I use Ollama and RagFlow to manage my own knowledge files, I upload some files to a knowledge，and they works well in the system. I start the ragflow with docker commands.
Who can help me to find the ...
- 13
1
vote
0
answers
193
views
How to handle follow-up confirmations in Spring AI 1.0.0 without losing context during tool selection using RAG?
I'm building a web application using Spring Boot 3.4.5 and Spring AI 1.0.0 with Llama3.2(Ollama) model integration. I've implemented tool calling, and because I have many tools in the application, I'm ...
-1
votes
1
answer
256
views
ImportError: cannot import name 'Client' from 'pinecone' (unknown location)
The problem with this piece of code is that I am unable to import Client from the pinecone library. I tried to uninstalling and reinstalling different versions none of them worked. I also tried it ...
- 11
0
votes
1
answer
268
views
Deleting data points in qDrant DB
I am trying to delete all the data points that are associated with a particular email Id, but I am encountering the following error.
source code:
app.get('/cleanUpResources', async (req, res) => {
...
0
votes
2
answers
545
views
GCP Vertex AI RAG Creation
Creating a RAG Corpus Using RAG and Storing Vector Search Information in the ragCorpus Endpoint
Tried the Following Approaches:
1️⃣ Unable to Create ragCorpus with Vertex Vector Search Info
Payload ...
1
vote
0
answers
680
views
Why is the upload of files to GCP Vertex AI RAG corpora so slow?
I am experimenting with RAG on GCP/Vertex AI, and tried to create some simple example.
Here's what I came up with, creating small dummy files locally and then uploading them one by one to a newly-...
- 6,039
0
votes
0
answers
172
views
Llamaindex returns "Empty Response"
I have a RAG system using llamaindex. I am upgrading library from 0.10.44 to 0.12.33.
I see a different behaviour now.
Before when there were not results from vectors store it seems it called the LLM ...
- 669
0
votes
1
answer
139
views
llama-index RAG: how to display retrieved context?
I am using LlamaIndex to perform retrieval-augmented generation (RAG).
Currently, I can retrieve and answer questions using the following minimal 5 line example, from https://docs.llamaindex.ai/en/...
- 1,802
1
vote
1
answer
698
views
How to keep updated information in a RAG system?
I have created a RAG system with documents I have (saved in chunks). I was wondering how to keep updated information in responses.
For example, I have news articles about one subject. Those articles ...
- 97
0
votes
2
answers
491
views
Passing request context from FastAPI to Microsoft Semantic Kernel Plugin for OpenAI Integration
I am integrating Microsoft Semantic Kernel with OpenAI in my FastAPI application. I have a chat/ endpoint where I receive a session_id from the request, and I need to pass this session_id to a plugin ...
1
vote
0
answers
94
views
Sentence similarity pipeline with @huggingface/transformers
Wanted to use the pipeline api from @huggingface/transformers js for sentence-similarity - but I do not see a specific pipeline for it.
The closest thing is text classification and feature extractions ...
- 1,020
0
votes
0
answers
129
views
Efficient Retrieval Methods of Relevant Chunks for Pydantic BaseModel for RAG Structured Output
I need to generate structured outputs using Pydantic’s BaseModel. Specifically, I need to retrieve relevant text chunks for each field in my model to minimize errors and ensure accurate data ...
0
votes
1
answer
264
views
Score Profiles Azure AI search not working
I have configured on my Index a default score profile to use on all of my searches, I have an test index that has a field named 'source' if the filed is == to 'reviewed' I want those docs to be moved ...
- 809
1
vote
1
answer
137
views
Embedding model `all-mpnet-base-v2` not able to classify user prompt properly
I am using this model to embed a product catalog for a rag. In the product catalog, there are no red shirts for men, but there are red shirts for women. How can I make sure the model doesnt output ...
0
votes
0
answers
99
views
How to loop through text chunks created using AzureOpenAI `client.vector_stores.create`
I checked Azure's documentation on this topic here but I do not see anything related to this. My goal is to create a question and answer dataset for my RAG solution based on each chunk for a good ...
- 3,629
-1
votes
1
answer
851
views
PDFSearchTool over multiple PDFs in CrewAI
How can I use the PDFSearchTool over multiple PDFs in CrewAI?
I’m currently using the PDFSearchTool and it works well with one single PDF but I didn’t find any example or managed to pass a list of ...
- 361
0
votes
1
answer
433
views
I am using LangChain4j to develop a knowledge base and encountered the "different vector dimensions 1024 and 384"
I want to know if there are any other settings required for pgvector or what content needs to be set in the code to enable pgvector to support higher vector dimensions. I found on the official website ...
- 3
1
vote
0
answers
61
views
Scaling RAG QA with Large Docs, Tables, and 30K+ Chunks (No LangChain)
I'm building a RAG-based document QA system using Python (no LangChain), LLaMA (50K context), PostgreSQL with pgvector, and Docling for parsing. Users can upload up to 10 large documents (300+ pages ...
- 11
0
votes
1
answer
146
views
Is it possible to share an Azure-based RAG chatbot without requiring users to sign in with Azure?
I’ve been experimenting with Azure AI Foundry and created a Retrieval-Augmented Generation (RAG) chatbot that works great on its own. However, when I try to deploy the chatbot using Azure, I encounter ...
0
votes
2
answers
75
views
SitemapLoader(sitemap_url).load() hangs
from langchain_community.document_loaders import SitemapLoader
def crawl(self):
print("Starting crawler...")
sitemap_url = "https://gringo.co.il/sitemap.xml"
...
- 28.8k
0
votes
1
answer
85
views
Compatibility Issues with Library Versions for RAG Project Integration with Rasa
I want to create a RAG (Retrieval-Augmented Generation) project and integrate it with Rasa. However, Rasa requires older versions of some libraries, such as Pydantic (version 1.10.10). Meanwhile, ...
1
vote
0
answers
47
views
how to deal with evolving information in RAG?
I'm trying to index a series of articles to use in a RAG knowledge base, I cannot find any best practice or recommendation documented about dealing with information that changes or evolves in time.
...
- 821
4
votes
2
answers
568
views
Can't make SafetySettings of VertexAI Gemini API work
I'm working on a RAG application using VertexAI API.
One of my questions has the word "roubar" and it keeps triggering the safety filter, like:
...
Candidate:
{
"index": 0,
&...
0
votes
0
answers
523
views
How to Build a Chatbot That Queries an SQL Database and Uses Vector Search for RAG?
I'm working on a chatbot that answers based on a department store's SQL database, and I need help.
The database looks like this:
If the user asks something like this:
The chatbot should answer like ...
0
votes
1
answer
162
views
Upserting in Pinecone takes too long
I'm trying to upsert reviews that i've scraped into pinecone. For the embedding model im using jina-embedding-v3. For 204 reviews this takes around 2.5 hours! in Colab. Tried using GPU but the ...
- 19
0
votes
0
answers
66
views
How to Extract Text Tables Images from PDFs while maintaining the structures
from unstructured library opensource one when i tried a pdf that have background images design patterns and XObjects in it this library also consider those as a images and store the path. so how can ...
- 11
-3
votes
1
answer
603
views
CREW AI tool not using ChatGroq
Here is my tools.py file
import os
from dotenv import load_dotenv
from langchain_groq import ChatGroq
from crewai_tools import PDFSearchTool, SerperDevTool
load_dotenv()
# Initialize the ChatGroq ...
- 115
1
vote
3
answers
1k
views
SemanticKernel with Plugin functions and vector database with C#
To start, I’d like to explain what I aim to achieve. My goal is to create an AI bot that will act as a hotel assistant, able to provide users with any hotel-related information they request. It should ...
- 1,207
0
votes
1
answer
599
views
AttributeError: 'LlmAgent' object has no attribute 'invoke'
I am trying to call Flask API which i alrady running on port 5000 on my system, i am desgning a agentic AI code which will invoke GET and then POSt based on some condition , and using google-adk. I ...
- 79
0
votes
1
answer
1k
views
Best approach for RAG using Azure OpenAI and AI Search with Python SDK [closed]
I struggle understanding what are the pros and cons of each one of these approaches for implementing a RAG using Azure OpenAI with AI Search as source, with Python SDK. Both work well, but option B ...
- 60
0
votes
2
answers
880
views
How to add S3 bucket objects metadata into bedrock knowledgebase?
I am using AWS bedrock for the first time. I have configured the data source which is S3 along with opensearch serverless cluster for embeddings. However, I do not have any control over the mappings ...
- 636