An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks
Home Page: https://www.thesamur.ai/?utm_source=github&utm_medium=link&utm_campaign=github_privategpt
License: MIT License
I am not that familiar with the python and the hardware part that llama-cpp-python and gpt4all require. Have you ever tried to put the application to a docker container?
can we use the gpu to get response more faster than use cpu ?
I trained the model using a PDF file of a book on ASO.
I asked "What is ASO?"
I get this answer (copied from the browser console to get the real response):
{"answer":"H9E,:?&+8&1<*<2E(#!=)G68/?5C/BGC,48BC292;3;1=%D$EC!;F%'-,81261/EB!52B159F26E49:15E!F4C(H17'&+#<\"'=F'A$)H;C?<(:9C\"H)F6=)8<+?.$'+B*2G/F:B7-4#,95C\"&E)&(,'12<);'(54<G37=,A'D#67E+\")E2*=+F$H*>$7$7BCE?#<1!:!=5<#6G\"*-D!>8'F8,B5A.;6*B!BA%(7/&>:G##=)3C->**'F-;GD+,$2","query":"how can i improve my app description","source":[{"name":"source_documents/The-Advanced-App-Store-Optimization_eBook_2022.pdf"},{"name":"source_documents/The-Advanced-App-Store-Optimization_eBook_2022.pdf"}]}
I tried using imartinez' privateGPT and there I get a valid, readable text response. I tried https://dencode.com/en/string but did not find any. So i'm not really sure what is going on. Does someone have an idea what is going on?
I have tried changing the code, but I have not succeeded yet, someone has already managed to install it with the model ggml-vic13b-q5_1.bin
???? thank you
C:>cd C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client
C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client>npm run dev
[email protected] dev C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client
next dev
C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client\node_modules\next\dist\cli\next-dev.js:256
showAll: args["--show-all"] ?? false,
^
SyntaxError: Unexpected token '?'
at Module._compile (internal/modules/cjs/loader.js:892:18)
at Object.Module._extensions..js (internal/modules/cjs/loader.js:973:10)
at Module.load (internal/modules/cjs/loader.js:812:32)
at Function.Module._load (internal/modules/cjs/loader.js:724:14)
at Module.require (internal/modules/cjs/loader.js:849:19)
at require (internal/modules/cjs/helpers.js:74:18)
at Object.dev (C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client\node_modules\next\dist\lib\commands.js:15:30)
at Object. (C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client\node_modules\next\dist\bin\next:150:28)
at Module._compile (internal/modules/cjs/loader.js:956:30)
at Object.Module._extensions..js (internal/modules/cjs/loader.js:973:10)
npm ERR! code ELIFECYCLE
npm ERR! errno 1
npm ERR! [email protected] dev: next dev
npm ERR! Exit status 1
npm ERR!
npm ERR! Failed at the [email protected] dev script.
npm ERR! This is probably not a problem with npm. There is likely additional logging output above.
npm ERR! A complete log of this run can be found in:
npm ERR! C:\Users\User\AppData\Roaming\npm-cache_logs\2023-05-29T07_17_34_828Z-debug.log
C:\Users\User\Documents\Learning\privateGPT2\privateGPT-main\client>
I want to know how to configure it so that it speaks to me in Spanish. Ask in Spanish and answer in Spanish. I don't understand why if I ask in Spanish he answers me in English
(pgweb) rex@alienware17B:~/pgweb/privateGPT/client$ npm run dev
[email protected] dev
next dev
/home/rex/pgweb/privateGPT/client/node_modules/next/dist/cli/next-dev.js:256
showAll: args["--show-all"] ?? false,
^
SyntaxError: Unexpected token '?'
at wrapSafe (internal/modules/cjs/loader.js:915:16)
at Module._compile (internal/modules/cjs/loader.js:963:27)
at Object.Module._extensions..js (internal/modules/cjs/loader.js:1027:10)
at Module.load (internal/modules/cjs/loader.js:863:32)
at Function.Module._load (internal/modules/cjs/loader.js:708:14)
at Module.require (internal/modules/cjs/loader.js:887:19)
at require (internal/modules/cjs/helpers.js:74:18)
at Object.dev (/home/rex/pgweb/privateGPT/client/node_modules/next/dist/lib/commands.js:15:30)
at Object. (/home/rex/pgweb/privateGPT/client/node_modules/next/dist/bin/next:150:28)
at Module._compile (internal/modules/cjs/loader.js:999:30)
How can I solve this problem? I've been struggling for a long time and can't find a solution. Please help me thanks!!!
Hello,
I run the command pip3 install -r requirements.txt and get this error
ERROR: Could not find a version that satisfies the requirement gpt4all==0.2.3 (from versions: 0.1.5, 0.1.6, 0.1.7) ERROR: No matching distribution found for gpt4all==0.2.3
Other than the web UI, are there functional difference over imartinez/privateGPT project?
After uploading a document, when asking questions, I get:
Error getting data.<!doctype html> <title>500 Internal Server Error</title>
The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/flask/app.py", line 2190, in wsgi_app
response = self.full_dispatch_request()
File "/usr/local/lib/python3.10/dist-packages/flask/app.py", line 1486, in full_dispatch_request
rv = self.handle_user_exception(e)
File "/usr/local/lib/python3.10/dist-packages/flask_cors/extension.py", line 165, in wrapped_function
return cors_after_request(app.make_response(f(*args, **kwargs)))
File "/usr/local/lib/python3.10/dist-packages/flask/app.py", line 1484, in full_dispatch_request
rv = self.dispatch_request()
File "/usr/local/lib/python3.10/dist-packages/flask/app.py", line 1469, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "/home/it/Scripts/PrivateChatGPT/server/privateGPT.py", line 146, in get_answer
res = qa(query)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 140, in call
raise e
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 134, in call
self._call(inputs, run_manager=run_manager)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/retrieval_qa/base.py", line 119, in _call
docs = self._get_docs(question)
File "/usr/local/lib/python3.10/dist-packages/langchain/chains/retrieval_qa/base.py", line 181, in _get_docs
return self.retriever.get_relevant_documents(question)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/base.py", line 377, in get_relevant_documents
docs = self.vectorstore.similarity_search(query, **self.search_kwargs)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/chroma.py", line 182, in similarity_search
docs_and_scores = self.similarity_search_with_score(query, k, filter=filter)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/chroma.py", line 229, in similarity_search_with_score
results = self.__query_collection(
File "/usr/local/lib/python3.10/dist-packages/langchain/utils.py", line 52, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/langchain/vectorstores/chroma.py", line 121, in __query_collection
return self._collection.query(
File "/usr/local/lib/python3.10/dist-packages/chromadb/api/models/Collection.py", line 227, in query
return self._client._query(
File "/usr/local/lib/python3.10/dist-packages/chromadb/api/local.py", line 437, in _query
uuids, distances = self._db.get_nearest_neighbors(
File "/usr/local/lib/python3.10/dist-packages/chromadb/db/clickhouse.py", line 585, in get_nearest_neighbors
uuids, distances = index.get_nearest_neighbors(embeddings, n_results, ids)
File "/usr/local/lib/python3.10/dist-packages/chromadb/db/index/hnswlib.py", line 240, in get_nearest_neighbors
raise NoIndexException(
chromadb.errors.NoIndexException: Index not found, please create an instance before querying
192.168.70.36 - - [30/May/2023 08:26:06] "POST /get_answer HTTP/1.1" 500 -
When I run the above command in powershell, it hand in certain point and like not continue process.
Import trace for requested module:
./node_modules/next/dist/lib/is-api-route.js
./node_modules/next/dist/shared/lib/router/router.js
./node_modules/next/dist/lib/is-error.js
There are multiple modules with names that only differ in casing.
This can lead to unexpected behavior when compiling on a filesystem with other case-semantic.
Use equal casing. Compare these module identifiers:
Import trace for requested module:
./node_modules/next/dist/lib/is-error.js
It stop here and few hour also not continue. May I know it's completed run? What cause this error?
When I run the localhost to download the language models and it gave me an error also.
Hi
when i hit download model return this error:
Unhandled Runtime Error
ReferenceError: response is not defined
Source
components/ConfigSideNav.js (27:3) @ response
25 | } catch (error) {
26 | setIsLoading(false);
> 27 | response.text().then(text => {toast.error("Error Ingesting data."+text);})
| ^
28 | }
29 | };
30 |
from flask import Flask,jsonify, render_template, flash, redirect, url_for, Markup, request
gptj_model_load: loading model from 'models/ggml-gpt4all-j-v1.3-groovy.bin' - please wait ...
gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx = 2048
gptj_model_load: n_embd = 4096
gptj_model_load: n_head = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot = 64
gptj_model_load: f16 = 2
gptj_model_load: ggml ctx size = 4505.45 MB
gptj_model_load: memory_size = 896.00 MB, n_mem = 57344
gptj_model_load: ................................... done
gptj_model_load: model size = 3609.38 MB / num tensors = 285
LLM0 GPT4All
Params: {'model': 'models/ggml-gpt4all-j-v1.3-groovy.bin', 'n_predict': 256, 'n_threads': 4, 'top_k': 40, 'top_p': 0.95, 'temp': 0.8}
How can I fix the issue ?
I had to get development deps setup before requirements.
apt install python3-dev make g++
pip install wheel
pip install -r requirements.txt
Upgrading langchain version to 0.0.177 in the requirements.txt file optimizes the RAM usage very well, I really recommend It.
Before downloading the model, create the models folder under server folder.
I removed the pywin32 module from the requirements, though I'm still getting errors when running install -r requirements.txt. This is the one I'm getting
ERROR: Could not find a version that satisfies the requirement putz-deprecation-shim==0.1.0.post0 (from versions: none)
ERROR: No matching distribution found for putz-deprecation-shim==0.1.0.post0
And when running privateGPT.py -- I'm getting the error below
File "/Users/XX/Desktop/privateGPT/server/privateGPT.py", line 1, in <module>
from flask import Flask,jsonify, render_template, flash, redirect, url_for, Markup, request
ModuleNotFoundError: No module named 'flask'
(base) XX@XXXX-iMac server % python3 privateGPT.py
Traceback (most recent call last):
File "/Users/am/Desktop/privateGPT/server/privateGPT.py", line 1, in <module>
from flask import Flask,jsonify, render_template, flash, redirect, url_for, Markup, request
ModuleNotFoundError: No module named 'flask'
Appreciate any support! :)
When I run "npm run dev" the console prints: '"next" is not an internal or external command, program or excecutable file.'
I finally got it to start, I uploaded a file, ingested data and then it downloaded until 32% and then this happened
`Traceback (most recent call last):
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 705, in _error_catcher
yield
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 830, in _raw_read
raise IncompleteRead(self._fp_bytes_read, self.length_remaining)
urllib3.exceptions.IncompleteRead: IncompleteRead(1236664320 bytes read, 2548583961 more expected)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\requests\models.py", line 816, in generate
yield from self.raw.stream(chunk_size, decode_content=True)
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 935, in stream
data = self.read(amt=amt, decode_content=decode_content)
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 874, in read data = self._raw_read(amt)
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 808, in _raw_read
with self._error_catcher():
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\contextlib.py", line 153, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\urllib3\response.py", line 722, in _error_catcher
raise ProtocolError(f"Connection broken: {e!r}", e) from e
urllib3.exceptions.ProtocolError: ('Connection broken: IncompleteRead(1236664320 bytes read, 2548583961 more expected)', IncompleteRead(1236664320 bytes read, 2548583961 more expected))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\flask\app.py", line 2190, in wsgi_app
response = self.full_dispatch_request()
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\flask\app.py", line 1486, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\flask_cors\extension.py", line 165, in wrapped_function
return cors_after_request(app.make_response(f(*args, **kwargs)))
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\flask\app.py", line 1484, in full_dispatch_request
rv = self.dispatch_request()
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\flask\app.py", line 1469, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "C:\Users\User\Downloads\privateGPT-main\server\privateGPT.py", line 190, in download_and_save
for chunk in response.iter_content(chunk_size=4096):
File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\requests\models.py", line 818, in generate
raise ChunkedEncodingError(e)
requests.exceptions.ChunkedEncodingError: ('Connection broken: IncompleteRead(1236664320 bytes read, 2548583961 more expected)', IncompleteRead(1236664320 bytes read, 2548583961 more expected))`
Running in /server
python privateGPT. error
Command 'python' not found, did you mean:
command 'python3' from deb python3
command 'python' from deb python-is-python3
or python3 privateGPT. error
python3: can't open file '/home/ai1/privateGPT/server/privateGPT.': [Errno 2] No such file or directory
Would specify in the requirements that this only works on windows. pywin doesn't work on other OS.
Use up the query is very slow, what is the way to make the query faster can try, thank you all, can use FAISS embedded database to solve the query slow
Unhandled Runtime Error
ReferenceError: response is not defined
Source
components\ConfigSideNav.js (27:3) @ response
25 | } catch (error) {
26 | setIsLoading(false);
27 | response.text().then(text => {toast.error("Error Ingesting data."+text);})
| ^
28 | }
29 | };
30 |
I have noticed that the app loads the model twice, using more RAM than needed. Is there a reason for that or is it just a bug?
I'm getting the following runtime error when running locally and after installing all the npm packages with npm i, as well as creating a venv for the python packages and installing all the requirements with pip.
"Unhandled Runtime Error
TypeError: event.target.file is undefined"
I'm facing an issue after uploading the document and successfully ingesting the data.
When I send a message in the prompt it says Error getting data and i get no response.
The server side terminal displays this -
127.0.0.1 - - [26/May/2023 16:13:19] "OPTIONS /get_answer HTTP/1.1" 200 -
Using embedded DuckDB with persistence: data will be stored in: db/
127.0.0.1 - - [26/May/2023 16:13:20] "POST /get_answer HTTP/1.1" 400 -
I have followed instructions, but when I go on localhost:3000 it gives the following errors.
When uploading document, it goes "Error uploading document"
When downloading model, it goes "Error downloading model"
When writing anything to the chat, it goes "Error fetching answer"
I tried to open PrivateGPT.py and it gave me this.
File "C:\Users\User\Downloads\privateGPT-main\server\privateGPT.py", line 1, in <module>
from flask import Flask,jsonify, render_template, flash, redirect, url_for, Markup, request
ModuleNotFoundError: No module named 'flask'
chromadb.errors.NoIndexException: Index not found, please create an instance before querying
127.0.0.1 - - [09/Jun/2023 15:36:36] "POST /get_answer HTTP/1.1" 500 -
Python3.9.0
Any idea?
I updated your code about client when upload file function error.
This code updated:
const handleFileChange = (event) => {
if (event.target.files && event.target.files.length > 0) {
setSelectedFile(event.target.files[0]);
}
};
Please update your code. Thanks.
operating system：CentOS Linux release 7.9.2009 (Core)
python：3.8.16（conda）
when i execute pip install -r requirements.txt
I have downloaded the ggml-gpt4all-j-v1.3-groovy.bin and ggml-model-q4_0.bin int the server->models folder. Then uploaded my pdf and after that ingest all are successfully completed but when I am querying anything then it gives the error of fetching answer | model not downloaded. How to resolve this issue?
README "pip install requirements" should be "pip install -r requirements" :)
Hey there! Thank you for providing such a tool, very cool!
Is it possible to switch the default language? I would really like to test in German.
Installation went fine with python 3.9
I notice even with two documents (from wikipedia article), and simple question, it still took long to get answer (around 10-15 mins).
How could i improve the answer time ?
I got this all setup with a few issues. Nothing ran into an issue when starting setup on the local environments. I took a simple text document, uploaded, ingest data - then when I go to Download model,
This is the error that is showing up...
No such file or directory 'models/ggml-gpt4all-j-v1.3-groovy.bin
[email protected] dev
next dev
(node:58556) ExperimentalWarning: stream/web is an experimental feature. This feature could change at any time
(Use node --trace-warnings ... to show where the warning was created)
node --trace-warnings ... to show where the warning was created)Error: listen EADDRNOTAVAIL: address not available 10.33.42.50
at Server.setupListenHandle [as _listen2] (node:net:1317:21)
at listenInCluster (node:net:1382:12)
at GetAddrInfoReqWrap.doListen [as callback] (node:net:1520:7)
at GetAddrInfoReqWrap.onlookup [as oncomplete] (node:dns:73:8)
Emitted 'error' event on Server instance at:
at emitErrorNT (node:net:1361:8)
at processTicksAndRejections (node:internal/process/task_queues:83:21) {
code: 'EADDRNOTAVAIL',
errno: -49,
syscall: 'listen',
address: '10.33.42.50'
}
I have downloaded a model
Uploaded a bitcoin white paper
Asked : What is that paper about and got
Using embedded DuckDB with persistence: data will be stored in: db/
[2023-05-29 00:45:56,320] ERROR in app: Exception on /get_answer [POST]
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/flask/app.py", line 2190, in wsgi_app
response = self.full_dispatch_request()
File "/usr/local/lib/python3.8/dist-packages/flask/app.py", line 1486, in full_dispatch_request
rv = self.handle_user_exception(e)
File "/usr/local/lib/python3.8/dist-packages/flask_cors/extension.py", line 165, in wrapped_function
return cors_after_request(app.make_response(f(*args, **kwargs)))
File "/usr/local/lib/python3.8/dist-packages/flask/app.py", line 1484, in full_dispatch_request
rv = self.dispatch_request()
File "/usr/local/lib/python3.8/dist-packages/flask/app.py", line 1469, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
File "privateGPT.py", line 146, in get_answer
res = qa(query)
File "/usr/local/lib/python3.8/dist-packages/langchain/chains/base.py", line 140, in __call__
raise e
File "/usr/local/lib/python3.8/dist-packages/langchain/chains/base.py", line 134, in __call__
self._call(inputs, run_manager=run_manager)
File "/usr/local/lib/python3.8/dist-packages/langchain/chains/retrieval_qa/base.py", line 119, in _call
docs = self._get_docs(question)
File "/usr/local/lib/python3.8/dist-packages/langchain/chains/retrieval_qa/base.py", line 181, in _get_docs
return self.retriever.get_relevant_documents(question)
File "/usr/local/lib/python3.8/dist-packages/langchain/vectorstores/base.py", line 377, in get_relevant_documents
docs = self.vectorstore.similarity_search(query, **self.search_kwargs)
File "/usr/local/lib/python3.8/dist-packages/langchain/vectorstores/chroma.py", line 182, in similarity_search
docs_and_scores = self.similarity_search_with_score(query, k, filter=filter)
File "/usr/local/lib/python3.8/dist-packages/langchain/vectorstores/chroma.py", line 229, in similarity_search_with_score
results = self.__query_collection(
File "/usr/local/lib/python3.8/dist-packages/langchain/utils.py", line 52, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/langchain/vectorstores/chroma.py", line 121, in __query_collection
return self._collection.query(
File "/usr/local/lib/python3.8/dist-packages/chromadb/api/models/Collection.py", line 227, in query
return self._client._query(
File "/usr/local/lib/python3.8/dist-packages/chromadb/api/local.py", line 437, in _query
uuids, distances = self._db.get_nearest_neighbors(
File "/usr/local/lib/python3.8/dist-packages/chromadb/db/clickhouse.py", line 585, in get_nearest_neighbors
uuids, distances = index.get_nearest_neighbors(embeddings, n_results, ids)
File "/usr/local/lib/python3.8/dist-packages/chromadb/db/index/hnswlib.py", line 240, in get_nearest_neighbors
raise NoIndexException(
chromadb.errors.NoIndexException: Index not found, please create an instance before querying
79.140.150.138 - - [29/May/2023 00:45:56] "POST /get_answer HTTP/1.1" 500 -
root@ns521942:/home/ubuntu/privateGPT/client/components#
I have tried to download a model and got this error:
Download Progress: 100.0%
Found model file.
gptj_model_load: loading model from 'models/ggml-gpt4all-j-v1.3-groovy.bin' - please wait ...
gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx = 2048
gptj_model_load: n_embd = 4096
gptj_model_load: n_head = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot = 64
gptj_model_load: f16 = 2
[2023-06-03 18:09:31,688] ERROR in app: Exception on /download_model [GET]
Traceback (most recent call last):
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\flask\app.py", line 2190, in wsgi_app
response = self.full_dispatch_request()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\flask\app.py", line 1486, in full_dispatch_request
rv = self.handle_user_exception(e)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\flask_cors\extension.py", line 165, in wrapped_function
return cors_after_request(app.make_response(f(*args, **kwargs)))
^^^^^^^^^^^^^^^^^^
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\flask\app.py", line 1484, in full_dispatch_request
rv = self.dispatch_request()
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\flask\app.py", line 1469, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\micha\privateGPT\server\privateGPT.py", line 197, in download_and_save
llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "pydantic\main.py", line 339, in pydantic.main.BaseModel.init
File "pydantic\main.py", line 1102, in pydantic.main.validate_model
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain\llms\gpt4all.py", line 139, in validate_environment values["client"] = GPT4AllModel(
^^^^^^^^^^^^^
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\gpt4all\gpt4all.py", line 49, in init
self.model.load_model(model_dest)
File "C:\Users\micha\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\gpt4all\pyllmodel.py", line 141, in load_model
llmodel.llmodel_loadModel(self.model, model_path.encode('utf-8'))
OSError: [WinError -1073741795] Windows Error 0xc000001d
127.0.0.1 - - [03/Jun/2023 18:09:31] "GET /download_model HTTP/1.1" 500 -
Is it possible to fix that?
Thank you and have a great day.
(pgweb) rex@alienware17B:~/pgweb/privateGPT/server$ python privateGPT.py
/home/rex/pgweb/privateGPT/server/privateGPT.py:1: DeprecationWarning: 'flask.Markup' is deprecated and will be removed in Flask 2.4. Import 'markupsafe.Markup' instead.
from flask import Flask,jsonify, render_template, flash, redirect, url_for, Markup, request
Traceback (most recent call last):
File "/home/rex/pgweb/privateGPT/server/privateGPT.py", line 213, in
load_model()
File "/home/rex/pgweb/privateGPT/server/privateGPT.py", line 210, in load_model
llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "pydantic/main.py", line 339, in pydantic.main.BaseModel.init
File "pydantic/main.py", line 1102, in pydantic.main.validate_model
File "/home/rex/miniconda3/envs/pgweb/lib/python3.11/site-packages/langchain/llms/gpt4all.py", line 170, in validate_environment
model_path=values["model"],
~~~~~~^^^^^^^^^
KeyError: 'model'
The port is occupied when starting the server. If I change the server port, where is the port changed when the client initiates the request?
Hello, I am also getting 404 not found when when going to http://192.168.20.50:5000/
Serving Flask app 'privateGPT'
Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
Running on all addresses (0.0.0.0)
Running on http://127.0.0.1:5000/
Running on http://192.168.20.50:5000/
Press CTRL+C to quit
192.168.70.36 - - [29/May/2023 15:48:07] "GET / HTTP/1.1" 404 -
http://192.168.20.50:3000/ works but can't upload a document gives error
Hi
After store model in directory run client/server, when ask question and send return this error:
Error Fetching Answer. Please try again.
Any idea?
Thanks
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.