Comments (7)
imartinez
commented on June 2, 2024
1
You probably didn't go through the "ingest" step, or the ingest didn't finish correctly. Run the ingest again and make sure a db folder with a subfolder and contents is created by that process. Then you can run privateGPT.py
from privategpt.
dennydream
commented on June 2, 2024
1
I ran into the same problem after trying a few things. Loaded 2 SEC filings-- had issues answering questions. Then tried loading Alice in Wonderland from the Gutenberg site. Loaded fine, asked a few questions. Then one question it appeared to run out of memory. closed down a few kernels in jupyter, then ran command line again and got this error.
from privategpt.
ottlinger
commented on June 2, 2024
I run into the same issue, but there is a db folder:
➜ db git:(main) ls
chroma-collections.parquet chroma-embeddings.parquet
➜ db git:(main)
from privategpt.
imartinez
commented on June 2, 2024
That's not looking good. It is missing the generated index folder. This is how it should look like after a successful ingestion:
db -> ls
chroma-collections.parquet chroma-embeddings.parquet index
db/index -> ls
id_to_uuid_42ad54d0-7908-4020-87db-b1f9fc9dad73.pkl index_metadata_42ad54d0-7908-4020-87db-b1f9fc9dad73.pkl
index_42ad54d0-7908-4020-87db-b1f9fc9dad73.bin uuid_to_id_42ad54d0-7908-4020-87db-b1f9fc9dad73.pkl
from privategpt.
ottlinger
commented on June 2, 2024
Thanks, I repeated the ingestion and this fixed the issue for me. Same with you @hktalent ?
from privategpt.
hktalent
commented on June 2, 2024
try:
python ingest.py
$ find db -type f|xargs -I % ls -alh %
-rw-r--r-- 1 51pwn staff 2.2M 5 12 18:14 db/chroma-embeddings.parquet
-rw-r--r-- 1 51pwn staff 3.3K 5 12 18:14 db/index/uuid_to_id_48798f7b-74a2-43d8-8e33-6e52bf3952ce.pkl
-rw-r--r-- 1 51pwn staff 2.8K 5 12 18:14 db/index/id_to_uuid_48798f7b-74a2-43d8-8e33-6e52bf3952ce.pkl
-rw-r--r-- 1 51pwn staff 1.4M 5 12 18:14 db/index/index_48798f7b-74a2-43d8-8e33-6e52bf3952ce.bin
-rw-r--r-- 1 51pwn staff 73B 5 12 18:14 db/index/index_metadata_48798f7b-74a2-43d8-8e33-6e52bf3952ce.pkl
-rw-r--r-- 1 51pwn staff 557B 5 12 18:14 db/chroma-collections.parquet
now
llama_print_timings: load time = 2760.40 ms
llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per run)
llama_print_timings: prompt eval time = 5753.98 ms / 32 tokens ( 179.81 ms per token)
llama_print_timings: eval time = 130.25 ms / 1 runs ( 130.25 ms per run)
llama_print_timings: total time = 5899.54 ms
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 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 token '�'
I do not know the answer as I am a machine learning model and do not have the capability to process human language or emotions. I am a language model trained on a vast amount of text data, and I am designed to provide general information, factual, or general knowledge based on my programming and data. If you need specific assistance with a human task or want a real person to talk to, I suggest contacting a live customer service representative for further assistance.
from privategpt.
hktalent
commented on June 2, 2024
Give up decisively, don't waste your life
from privategpt.
Related Issues (20)
- Security And Privacy Concerns for input data on latest release HOT 1
- Query Multiple Files HOT 1
- CSV/Tabular data not working
- User Auth feature HOT 1
- Installing LLAMA CUDA libraries and Python bindings ERROR HOT 1
- Fail to run PGPT_PROFILES=ollama make run
- Changing embedding parameters
- JSON Formatted Output
- ModuleNotFoundError: No module named 'gradio'
- Can invoke LLM for twice. HOT 1
- Evaluation by RAGAs
- Bulk Local Injestion: How to initiate from Dockerfile? & "--watch" is not working
- Has anyone had any success with creating a questions file feeding PrivateGPT? HOT 1
- Change chunking/splitting method from SentenceWindowNodeParser to SentenceSplitter or SemanticSplitterNodeParser HOT 2
- Logger doesn't log my custom log
- "Make wipe" does not reset the qdrant database HOT 1
- File not present as "ingested file" after uploading with openai configuration
- JPEG files not ingested with the local Ollama recommended setup. HOT 1
- Error occurs when "make run" on Win11 HOT 2
- (e.g., hello-world-python) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from privategpt.