LlamaIndex
Log in

Find answers from the community

Home
Members
mr.niko.la
m
mr.niko.la
Offline, last seen 2 months ago
Joined September 25, 2024
mmr.niko.la
·

Ollama

is there change to this loader ?

‘’’

ollama_pack = OllamaQueryEnginePack(model="stablelm-zephyr", documents=documents)

TypeError: init() takes 1 positional argument but 2 were given#
‘’’
7 comments
m
L
mmr.niko.la
·

Using `TogetherAI`

Using TogetherAI

Plain Text
    embedding_model: str = "togethercomputer/m2-bert-80M-8k-retrieval",
    generative_model: str = "mistralai/Mixtral-8x7B-Instruct-v0.1",


For chating with a folder full of invoices, pdf ,datasheet

This was from Feb script.
Is there a better embedding_model and generative_model to use?
2 comments
R
mmr.niko.la
·

LLM

Is possible to use together.ai api endpoint with llama-index ?
25 comments
m
L
f
W
mmr.niko.la
·

```

Plain Text
from llama_index.llama_pack import download_llama_pack

# download and install dependencies,  comment if already downloaded
OllamaQueryEnginePack = download_llama_pack("OllamaQueryEnginePack", "./ollama_pack")


anyone know how to reinitiate thie OllamaQueryEnginePack after editing base.py
64 comments
m
L
mmr.niko.la
·

The llamapack code just needs to be

The llamapack code just needs to be updated.

Does anyone no how to Download the pack and edit the code…

Plain Text
llm = Ollama(model=self_model, base_url=self._base_url)
17 comments
m
L
mmr.niko.la
·

Very easy to prototype but can get

Very easy to prototype but can get complicated for production. Also curious to see how others are doing it. Weather they are internal or external dev
6 comments
T
K
m
mmr.niko.la
·

```

Plain Text


is this happen when you run out of memory?

im running dolphin-phi on 5600g amd apu using ollama
21 comments
L
m