31 questions
0
votes
0
answers
98
views
How can I persist a db for MultiVectorRetriever?
I am trying to build a RAG from pdfs where I extract the text and tables. I want to use a persistent db in order to store the chunks, tables, embeddings e.t.c. and then reload the db and use the ...
- 339
0
votes
0
answers
72
views
Error embedding content: 504 Deadline Exceeded
So when i try to generate embeddings from two different types of codes -
here is the one which is mentioned on the langchain site but this gives me deadline exceed
@lru_cache
def get_settings():
...
0
votes
1
answer
468
views
How to properly initialize and query a PGVectorStore with metadata columns in LangChain?
I'm trying to use PGVectorStore in LangChain with metadata columns, following the example in pypi page, but I'm encountering issues when attempting to add and query documents with metadata. The basic ...
- 103
0
votes
1
answer
53
views
problem with prompting using FAISS as a vector store to classify dialogs based on sentiment emotions
I have a .csv dataset consisting of text dialog between two people and the rating of the related emaotions:
| Text_Dialog | joy | anger | sad | happy |
|--------------------|-----|-------|-----|...
- 101
0
votes
0
answers
116
views
Llama Index Vector Store: filter a list of documents with a NOT feature
I have a vector store of documents, each document is a json document with features. I'd like to filter the documents according to some criteria. The problem is that some of the documents contain a NOT ...
- 923
0
votes
0
answers
113
views
How to expand context window based on metadata of the vector-store collection
I have a working RAG code, using Langchain and Milvus. Now I'd like to add the feature to look at the metadata of each of the extracted k documents, and do the following:
find the paragraph_id of ...
- 512
0
votes
1
answer
124
views
Langchain Cohere embeddings says "invalid type: parameter texts is of type object but should be of type string" inspite of receiving strings
This part of the code, specifically the part where rag_chain is invoked causes an error:
Retrying langchain_cohere.embeddings.CohereEmbeddings.embed_with_retry.<locals>._embed_with_retry in 4.0 ...
- 61
0
votes
0
answers
25
views
How do I use MergeDataLoader to tolerate multiple files that could be in either PDF or docx format?
I am writing a RAG chatbot that retrieves information from a given list of documents. The documents can be found in a set folder, and they could be either .pdf or .docx. I want to merge all the ...
1
vote
0
answers
240
views
Vector dimensions mismatch in OpenSearch vector store using BedrockEmbeddings
I'm using a vector store that I've created in AWS OpenSearch serverless. It has one index that has below configurations:
- Engine: faiss
- Precision: Binary
- Dimensions: 1024
- Distance Type: ...
- 11
0
votes
1
answer
1k
views
How to Check if a Document Exists in a Chroma Vectorstore Using LangChain?
I am using a vectorstore of some documents in Chroma and implemented everything using the LangChain package. Here’s the package I am using:
from langchain_chroma import Chroma
I need to check if a ...
- 1
0
votes
1
answer
295
views
Problem Setting up a FAISS vector memory in Python with embeddings
I'm trying to run an LLM locally and feed it with the contents of a very large PDF. I have decided to try this via a RAG. For this I wanted to create a vectorstore, which contains the content of the ...
- 428
2
votes
1
answer
233
views
vector store stuck with file counts in_progress or vector store is empty
I am trying to upload 2 json files into an assistants vector store using the official openAI python library. I also want to use a specific chunking strategy, and a different one for each files.
There ...
- 21
1
vote
1
answer
364
views
Is there a way to load a saved SKLearn VectorStore using langchain?
I created and saved a vectorstore using langchain_community.vectorstores SKLearnVectorStore and I can't load it.
I created and saved vectorstore as below:
from langchain_community.vectorstores import ...
- 33
0
votes
1
answer
103
views
How to query the vector database in LangChain AgentExecutor, invoice before summarizing the 'Final Answer' after all tools have been called?
How to query the vector database in LangChain AgentExecutor, invoice before summarizing the 'Final Answer' after all tools have been called?
LangChain AgentExecutor code:
llm = ChatOpenAI()
tools = [...
- 75
0
votes
1
answer
366
views
Issue with Storing and Loading Index Timescale Vector Llama Index
I'm currently working with the llama_index Python package and using the llama-index-vector-stores-timescalevector extension to manage my vectors with Timescale. However, I’ve encountered an issue ...
0
votes
0
answers
171
views
OPENSSL_internal:CERTIFICATE_VERIFY_FAILED error when vector_store retriever is invoked
I'm in the midst of developing Genai app with
private data stored in vertex ai vector db
llm as gpt4
langhain as orchestrator
When I invoke vector_store retriever I get error:
OPENSSL_internal:...
1
vote
1
answer
264
views
Spring-AI : How to connect Redis VectorStore?
According to this commit, I now need to connect using RedisAutoConfiguration instead of RedisVectorStoreAutoConfiguration and I'm curious about how.
commit comment
Here is the Redis connection ...
- 11
0
votes
0
answers
524
views
Not able to create asynchronous chromadb
I'd like to create a status_checker api endpoint in fastapi to track the creation of chromadb embeddings. Also I'd like to create these embeddings in async mode. Below is the code, but it is giving ...
0
votes
1
answer
109
views
Does SelfQueryRetriever works with chromadb server(collections)?
I am currently working with SelfQueryRetriever and my data is stored in a ChromaDB server within a collection. While a simple similarity search retrieves answers correctly, using SelfQueryRetriever ...
- 1
2
votes
0
answers
308
views
Random"IndexError: list index out of range issue" OpenAI's "messages = list(client.beta.threads.messages.list(thread_id=thread.id, run_id = run.id))"
The code works a few iterations of the following:
Creating vector store
Upload individual file (to ensure clean and singular context)
Call OpenAI's "client.beta.threads.runs.create_and_poll"...
- 21
0
votes
1
answer
237
views
Check the existence of records in the elastic search vector store
I have such entries in my elasticsearch index:
It's unstructured data, in this case the content of a PDF that was split into chunks, then a LangChain document was created for each chunk and pushed to ...
- 679
3
votes
0
answers
347
views
Error creating single-field vector index in Firestore with gcloud CLI
I'm trying to create a single-field vector index in my Firestore database using the gcloud command-line interface (CLI) to enable vector search functionality.
However, I keep getting this error:
...
- 3,007
3
votes
1
answer
2k
views
Kernel crashes when running a FAISS similarity search
I am working with langChain right now and created a FAISS vector store. Since today, my kernel crashes when running a similarity search on my vector store. Has anyone an idea why this is happening?
...
- 33
1
vote
0
answers
180
views
AttributeError: 'Tensor' object has no attribute 'embed_documents'
I have uploaded PDF file and split file into chunks, then apply tokenizer to each chunck and created embeddings. But when i try to store my embedding in FIASS, it give me AttributeError: 'Tensor' ...
0
votes
1
answer
571
views
Why am I getting a TypeError: string indices must be integers, not 'str' when cutting up documents into chunks with Python and langchain?
Following is some code that I'm working on using Python and langchain to ingest a PDF document into a vector store for consumption as a reference manual for an AI initiative I'm working on.
...
1
vote
1
answer
3k
views
failed to create query: Field 'vector_field' is not knn_vector type
I am using Aws Bedrock + langchain +openSerach Vector store.
when i ask question to RAG base chatbot it gives me error like "failed to create query: Field 'vector_field' is not knn_vector type.&...
- 55
0
votes
1
answer
488
views
"object tuple can't be used in 'await' expression" while using OpensearchVectorClient for llama-index
I'm trying to use OpensearchVectorClient() function in llama-index, but I've run into a problem while calling OpenSearch: "object tuple can't be used in 'await' expression".
Here my code:
...
0
votes
1
answer
2k
views
How to retrieve ids and metadata associated with embeddings of a particular pdf file and not just for the entire collection chromadb?
I am working on a chat application in Langchain, Python. The idea is that user submits some pdf files that the chat model is trained on and then asks questions from the model regarding those documents....
1
vote
0
answers
1k
views
Load Chroma vectorstore from disk
I have created a vectorstore using Chroma and Langchain with three different collections and stored it in a persistent directory using the following code:
def create_embeddings_vectorstorage(splitted):...
1
vote
0
answers
1k
views
AttributeError: 'function' object has no attribute 'embed_query' using Langchain FAISS vectorstore
I'm following AWS Bedrock workshop here - https://github.com/aws-samples/amazon-bedrock-workshop/blob/main/03_QuestionAnswering/01_qa_w_rag_claude.ipynb. Everything is working fine until I go to the ...
- 11
1
vote
2
answers
643
views
Is Per-User Retrieval supports open-source vectorstore chromadb?
From the langchain documentation - Per-User Retrieval
When building a retrieval app, you often have to build it with multiple users in mind. This means that you may be storing data not just for one ...
- 3,025