Questions tagged [ollama]
Ollama is a product for running Llama 2, Code Llama and other large language models.
ollama
145
questions
0
votes
0
answers
7
views
How to view the final prompt in a MultiQueryRetriever pipeline using LangChain?
I am currently working on a project using the LangChain library where I want to retrieve relevant documents from a vector database and then generate answers based on these documents using the Ollama ...
0
votes
0
answers
39
views
Ollama Embedding using nomic-embed-text without locally installed instance
import gradio as gr
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import pdf
from langchain_community.vectorstores import Chroma
from ...
0
votes
0
answers
24
views
Fine-tune LLM on custom schema to be used in sqlcoder, an ollama based llm
I am working on a POC to convert Natural language to SQL. I have used phi3 and now planning to use sqlcoder as part of the llm. All this are set up via ollama which I am running on docker.
The one ...
0
votes
0
answers
20
views
LLama 2 prompt template
I am trying to build a chatbot using LangChain. This chatbot uses different backend:
Ollama
Huggingfaces
LLama.cpp
Open AI
and in a YAML file, I can configure the back end (aka provider) and the ...
0
votes
1
answer
47
views
ImportError: cannot import name 'Ollama' from 'langchain.llms'
Trying to test Ollama customised promt in the vitural environment[.venv (Python 3.11.9] locally in VS Code .ipynb file. However, getting the following error message:
Error:
ImportError: cannot import ...
0
votes
1
answer
57
views
unable to implement streaming while generating response of ollama
I am using langchain4j, PGVector and Ollama (llama3) for my RAG application
there is an API endpoint "/generate" where the user gives a string and it returns the response generated by the ...
0
votes
0
answers
37
views
ConnectError: All connection attempts failed when connecting indexing to neo4j database using PropertyGraphIndex from llama3
I am working on knowledge graph and all connection to neo4j browser is a success(using neo4j desktop windows not docker deployed). however with llama3 i am running the same notebooks as in property ...
1
vote
0
answers
79
views
+50
How to immediately cancel an Asyncio Task that uses the Ollama Python library to generate an answer?
I'm using Ollama to generate answers from large language models (LLMs) with the Ollama Python API. I want to cancel the response generation by clicking the stop button. The problem is that the task ...
0
votes
1
answer
51
views
Does langchain with llama-cpp-python fail to work with very long prompts?
I'm trying to create a service using the llama3-70b model by combining langchain and llama-cpp-python on a server workstation. While the model works well with short prompts(question1, question2), it ...
0
votes
0
answers
50
views
How should I use Llama-3 properly?
I downloaded the Meta-Llama-3-70B-Instruct model using the download.sh and the url provided by Meta email, and this is all the files in the folder.
enter image description here
And when I tried to use ...
0
votes
1
answer
130
views
Slow Ollama API - how to make sure the GPU is used
I made a simple demo for a chatbox interface in Godot, using which you can chat with a language model, which runs using Ollama. Currently, the interface between Godot and the language model is based ...
0
votes
0
answers
38
views
How to use the godot-llama-cpp plugin
Godot newbye here. I made a simple chatbot demo (repo here) in Godot, which takes as input the text typed by a user and outputs the replies generated by a large language model running locally using ...
-1
votes
0
answers
321
views
Ollama erro (HTTPError: 404 Client Error: Not Found for url: http://localhost:11434/v1/chat/completions)
I'm trying to translate the results I scraped using Selenium.
But have been facing same issue while using ollama.
Here's the error in detail with my codes.
import os
import openai
import requests
...
3
votes
0
answers
80
views
langchain4j and Ollama - chat does not work because of uppercased role value
I am using Ollama v0.2.3 on Windows with tinyllama, locally installed, and langchain4j v0.32.0.
I followed a very simple example of sending a chat query to Ollama.
To my surprise I got back a very ...
0
votes
0
answers
189
views
How to stop Ollama model streaming
So I have this class that streams the response form a model:
from langchain_community.llms.ollama import Ollama
from app.config import (
LLM_MODEL_NAME,
MAX_LLM_INPUT_LENGTH,
...