private-gpt

private-gpt copied to clipboard

Error building llama-cpp-python hnswlib

11

Would you help me to fix it? Thanks a lot, Iim tring to install the package using pip install -r requirements.txt All is going OK untill this point: ---------- Building...

lsotillos

volume of text?

8

What kind of corpus of text is reasonable to bring in, do you think? A few megabytes, a few gigabytes or perhaps more?

glinkot

chromadb error

16

Hey, I love the idea behind this repo, keep up the good work. I am getting the following error: ``` Traceback (most recent call last): File "/Users/tjones/Projects/privateGPT/privatechatenv/lib/python3.10/site-packages/langchain/vectorstores/chroma.py", line 111, in...

TylerWJ

gpt_tokenize: unknown token '?'

24

gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown token '?' gpt_tokenize: unknown...

anonimo28

Import error when ingesting

1

> `ImportError: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with LibreSSL 2.8.3. See: https://github.com/urllib3/urllib3/issues/2168` Unable to ingest any document due to this.

Swader

line 223, in get_nearest_neighbors raise NoIndexException("Index not found, please create an instance before querying")

3

Hi, thanks for creating this incredible tool. I have been able to parse the .txt file correctly, and `python privateGPT.py` runs fine, outputting the "Enter a query". But when this...

0xking-sol

llama.cpp: can't use mmap because tensors are not aligned; convert to new format to avoid this

21

llama.cpp: loading model from ./models/ggml-model-q4_0.bin llama.cpp: can't use mmap because tensors are not aligned; convert to new format to avoid this llama_model_load_internal: format = 'ggml' (old version with low tokenizer...

rexzhang2023

how to utilize GPU where I am using WSL with Ubuntu2204

4

I have follow ubuntu website to install CUDA with my WSL distro. When I run privategpt, seems it do NOT use GPU at all. is there any support for that?...

rexzhang2023

Suggestions for speeding up ingestion?

17

I presume I must be doing something wrong, as it is taking hours to ingest a 500kbyte text on an i9-12900 with 128GB. In fact it's not even done yet....

pinballelectronica

Any chance of PDF ingestion?

6

RuairiSpain