Document Chatbot — multiple files. Powered by GPT / Embedding.
License: MIT License
🔭 I’m currently working on ChatFiles
🌱 I’m currently learning GenAI
👯 I’m looking to collaborate on ChatFiles
📝 I regularly write articles on https://guangzhengli.com
📫 How to reach me [email protected]
⚡ Fun fact Running & Reading
In the process of starting the service for the first time, this kind of error is reported.
What should I do?
The following is the full text of the whole error message.
PS D:\KKK_usual tools\ChatFiles-main> docker compose up
[+] Running 2/0
I've had this error when I run locally. But it works well when using your image docker.
Unhandled Runtime Error
Error: Objects are not valid as a React child (found: object with keys {error, success}). If you meant to render a collection of children, use an array instead.
Someone has any clue about this?
The string did not match the expected pattern..
第一个问题给我回复了引用的一篇文献的标题，第二第三个问题等于没有回答，显得特别智障，不知道是不是我用法出错了
2023-04-11 21:07:23 chatfiles-ui | beginning handler
2023-04-11 21:07:23 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:07:23] "POST /upload HTTP/1.1" 200 -
2023-04-11 21:07:38 chatfiles-ui | beginning handler
2023-04-11 21:07:38 chatfiles-ui | handler chatfile query: can you describe this article for me?? garnet 配位数计算.json
2023-04-11 21:07:38 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:07:38] "GET /query?message=can%20you%20describe%20this%20article%20for%20me??&indexName=garnet%20配位数计算.json HTTP/1.1" 404 -
2023-04-11 21:08:01 chatfiles-ui | beginning handler
2023-04-11 21:08:10 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens
2023-04-11 21:08:10 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 33459 tokens
2023-04-11 21:08:10 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:08:10] "POST /upload HTTP/1.1" 200 -
2023-04-11 21:10:35 chatfiles-ui | beginning handler
2023-04-11 21:10:35 chatfiles-ui | handler chatfile query: can you describe this article for me? Garnets geochemical and exploration implication
2023-04-11 21:11:37 chatfiles | WARNING:/usr/local/lib/python3.8/site-packages/langchain/chat_models/openai.py:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised Timeout: Request timed out: HTTPSConnectionPool(host='api.openai.com', port=443): Read timed out. (read timeout=60).
2023-04-11 21:12:08 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 460 tokens
2023-04-11 21:12:08 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 8 tokens
2023-04-11 21:12:08 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:12:08] "GET /query?message=can%20you%20describe%20this%20article%20for%20me?&indexName=Garnets%20geochemical%20and%20exploration%20implication HTTP/1.1" 200 -
2023-04-11 21:13:15 chatfiles-ui | beginning handler
2023-04-11 21:13:20 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens
2023-04-11 21:13:20 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 21617 tokens
2023-04-11 21:13:20 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:13:20] "POST /upload HTTP/1.1" 200 -
2023-04-11 21:13:31 chatfiles-ui | beginning handler
2023-04-11 21:13:31 chatfiles-ui | handler chatfile query: can you describe this article for me? garnet 配位数
2023-04-11 21:14:02 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 321 tokens
2023-04-11 21:14:02 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 8 tokens
2023-04-11 21:14:02 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:14:02] "GET /query?message=can%20you%20describe%20this%20article%20for%20me?&indexName=garnet%20配位数 HTTP/1.1" 200 -
2023-04-11 21:14:59 chatfiles-ui | beginning handler
2023-04-11 21:14:59 chatfiles-ui | handler chatfile query: can you translate the abstract part into Chinese? garnet 配位数
2023-04-11 21:15:26 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 309 tokens
2023-04-11 21:15:26 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 9 tokens
2023-04-11 21:15:26 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:15:26] "GET /query?message=can%20you%20translate%20the%20abstract%20part%20into%20Chinese?&indexName=garnet%20配位数 HTTP/1.1" 200 -
2023-04-11 21:17:30 chatfiles-ui | beginning handler
2023-04-11 21:17:30 chatfiles-ui | handler chatfile query: summary the Introduction part garnet 配位数
2023-04-11 21:18:04 chatfiles | INFO:openai:error_code=None error_message='That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID 9292f425210eb6ff2b6db4990b291e20 in your message.)' error_param=None error_type=server_error message='OpenAI API error received' stream_error=False
2023-04-11 21:18:04 chatfiles | WARNING:/usr/local/lib/python3.8/site-packages/langchain/chat_models/openai.py:Retrying langchain.chat_models.openai.ChatOpenAI.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID 9292f425210eb6ff2b6db4990b291e20 in your message.).
2023-04-11 21:19:00 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 3944 tokens
2023-04-11 21:19:00 chatfiles | INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 4 tokens
2023-04-11 21:19:00 chatfiles | INFO:werkzeug:172.18.0.3 - - [11/Apr/2023 13:19:00] "GET /query?message=summary%20the%20Introduction%20part&indexName=garnet%20配位数 HTTP/1.1" 200 -
(base) u20@u20:/ChatFiles$ docker --version/ChatFiles$ ../flyctl launch
Docker version 23.0.5, build bc4487a
(base) u20@u20:
Update available 0.0.475 -> v0.0.559.
Run "flyctl version update" to upgrade.
An existing fly.toml file was found for app chatfiles2
App is not running, deploy...
==> Building image
Remote builder fly-builder-withered-forest-5301 ready
Error failed to fetch an image or build from source: app does not have a Dockerfile or buildpacks configured. See https://fly.io/docs/reference/configuration/#the-build-section
I tried several ways for streaming response but no success can anyone share me
This project is interesting, however, the current docker image supports only arm/v8, to use it on amd64 machine you need to build it manually, which is not convenient.
Suggestion: use GitHub action to build the image.
drag and drop is not working on demo and locally deployed instance.
可以支持多用户
可以支持已有文件索引列表的展示及管理
可以支持远程文件的读取分析，输入URL即可，这个其实很容易的
支持token统计及openAI详细的错误露出，以方便调试。
when i ask for a code i got this why?:
handler chatfile query: cual seria la ultima que menciona scrapy-think-splash-rich-fastapi-merged
beginning handler
handler chatfile query: puedes revisar este codigo? import scrapyfrom scrapy_splash import SplashRequestfrom rich.prompt import Promptfrom rich.table import Tablefrom rich.console import Consoleclass MySpider(scrapy.Spider): name = 'myspider' def start_requests(self): urls = Prompt.ask("Enter one or more URLs separated by commas: ") urls = urls.split(",") for url in urls: if self.should_use_splash(url): yield SplashRequest(url, self.parse, args={'wait': 1}, endpoint='render.html', splash_headers={ 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3' } ) else: yield scrapy.Request(url, self.parse) def should_use_splash(self, url): if "javascript" in url: return True undefined
API resolved without sending a response for /api/query?message=puedes%20revisar%20este%20codigo?%20import%20scrapyfrom%20scrapy_splash%20import%20SplashRequestfrom%20rich.prompt%20import%20Promptfrom%20rich.table%20import%20Tablefrom%20rich.console%20import%20Consoleclass%20MySpider(scrapy.Spider):%20%20%20%20name%20=%20%27myspider%27%20%20%20%20def%20start_requests(self):%20%20%20%20%20%20%20%20urls%20=%20Prompt.ask(%22Enter%20one%20or%20more%20URLs%20separated%20by%20commas:%20%22)%20%20%20%20%20%20%20%20urls%20=%20urls.split(%22,%22)%20%20%20%20%20%20%20%20for%20url%20in%20urls:%20%20%20%20%20%20%20%20%20%20%20%20if%20self.should_use_splash(url):%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20yield%20SplashRequest(url,%20self.parse,%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20args={%27wait%27:%201},%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20endpoint=%27render.html%27,%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20splash_headers={%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%27user-agent%27:%20%27Mozilla/5.0%20(Windows%20NT%2010.0;%20Win64;%20x64)%20AppleWebKit/537.36%20(KHTML,%20like%20Gecko)%20Chrome/58.0.3029.110%20Safari/537.3%27%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20}%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20)%20%20%20%20%20%20%20%20%20%20%20%20else:%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20%20yield%20scrapy.Request(url,%20self.parse)%20%20%20%20def%20should_use_splash(self,%20url):%20%20%20%20%20%20%20%20if%20%22javascript%22%20in%20url:%20%20%20%20%20%20%20%20%20%20%20%20return%20True%20%20%20%20%20%20%20%20, this may result in stalled requests.
^C
我在dockerfiles已经添加了安装pytorch和TensorFlow的指令。
但是在运行docker镜像的时候，依然会提示"没有构建“pytorch或者TensorFlow”的信息。
因为某些原因国内无法直接访问 OpenAI API，如果能添加 自定义 API 请求地址，就可以使用如 API2D 这样的中转服务了。
我尝试在 docker-composer 和 server.py 加了下参数，但似乎不生效 😶
Hi, nice work!
sadly however, i've not been able to change the model to gpt-4..
if i change this line like so in the llm.py
llm_predictor = LLMPredictor(llm=ChatOpenAI(
temperature=0.2, model_name="gpt-4"))i am seeing this error in the interface JSON.parse: unexpected character at line 1 column 1 of the JSON data.
and this in the shell
error - FetchError: request to http://127.0.0.1:5000/upload failed, reason: connect ECONNREFUSED 127.0.0.1:5000
at ClientRequest.<anonymous> (file:///C:/Users/sbene/Projects/ChatFiles-main/chatfiles-ui/node_modules/node-fetch/src/index.js:108:11)
at ClientRequest.emit (node:events:525:35)
at Socket.socketErrorListener (node:_http_client:494:9)
at Socket.emit (node:events:513:28)
at emitErrorNT (node:internal/streams/destroy:151:8)
at emitErrorCloseNT (node:internal/streams/destroy:116:3)
at process.processTicksAndRejections (node:internal/process/task_queues:82:21) {
type: 'system',
errno: 'ECONNREFUSED',
code: 'ECONNREFUSED',
erroredSysCall: 'connect',
page: '/api/upload'
}
错误log：
from llm import get_index_by_index_name File "/Users/axzq/code/python/ChatFiles/chatfiles/llm.py", line 18, in <module> service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/indices/service_context.py", line 71, in from_defaults embed_model = embed_model or OpenAIEmbedding() File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/embeddings/openai.py", line 209, in __init__ super().__init__(**kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/embeddings/base.py", line 55, in __init__ self._tokenizer: Callable = globals_helper.tokenizer File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/utils.py", line 38, in tokenizer enc = tiktoken.get_encoding("gpt2") File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/tiktoken/registry.py", line 63, in get_encoding enc = Encoding(**constructor()) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/tiktoken_ext/openai_public.py", line 11, in gpt2 mergeable_ranks = data_gym_to_mergeable_bpe_ranks( File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/tiktoken/load.py", line 90, in data_gym_to_mergeable_bpe_ranks encoder_json = json.loads(read_file_cached(encoder_json_file)) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/tiktoken/load.py", line 46, in read_file_cached contents = read_file(blobpath) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/tiktoken/load.py", line 24, in read_file return requests.get(blobpath).content File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/requests/api.py", line 73, in get return request("get", url, params=params, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/requests/api.py", line 59, in request return session.request(method=method, url=url, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/requests/sessions.py", line 587, in request resp = self.send(prep, **send_kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/requests/sessions.py", line 701, in send r = adapter.send(request, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/requests/adapters.py", line 563, in send raise SSLError(e, request=request) requests.exceptions.SSLError: HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /gpt-2/encodings/main/encoder.json (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:997)')))
如题
上传一个文件，问文件主题是啥，回答都是 None
hi,
i tried to upload the PDF file, while there was no error during the upload process, however after the process is done, instead of showing name of the file on top, it shows some unparsed html code. please check the attached images:
设置为zh语言，但是没有效果，我也配置了zh 下面的 common
Hi @guangzhengli is it possible chatfiles can be deployed in azure web app container? I'm trying to deploy it but getting 404 error.
Im using this config in the azure container config for docker-compose.
version: '2.2' services: chatfiles: image: newpdfairegistry.azurecr.io/chatfiles-chatfiles:latest container_name: chatfiles ports: - 5000:5000 chatfiles-ui: image: newpdfairegistry.azurecr.io/chatfiles-chatfiles-ui:latest container_name: chatfiles-ui ports: - 3000:3000 - CHAT_FILES_SERVER_HOST=https://chatfiles3.azurewebsites.net:5000 - NEXT_PUBLIC_CHAT_FILES_MAX_SIZE=0 depends_on: - chatfiles
这个我看到已经实现了？但是最新版本要怎么操作呢，目前上传文件还是只能上传一个
如题，另外想知道「上传多个文件，构建同一个 Index，然后与之对话。」这个feature大概什么时候能好，或者说告诉下我实现原理，我自己试试看，多谢~
在按照 requirements.txt 里的要求安装完依赖环境之后，上传文件就会提示：
File: Error: The constructor now takes in a list of Node objects. Since you are passing in a list of Document objects, please use
from_documentsinstead.
不知道该怎么解决，辛苦您帮我看一下是不是我哪里做错了。
我看本项目用了LlamaIndex和langchain，我看简介好像是这两个项目或库能调用其他的开源大语言模型，但我是小白、不确定，详情大神确认一下。
如果是的， 该怎么修改代码呢？非常感谢！
works cool!!! thanks, just a few questions:
在本地端分別運行 chatfiles-ui 與 chatfiles
已經在 /chatfiles 下建好 .env，並設定 OPENAI_API_KEY=XXXXX
但運行起來後又方文字提示 OpenAI API Key Required
到左下角將 Key 輸入後仍顯示
Error fetching models.
Make sure your OpenAI API key is set in the bottom left of the sidebar.
If you completed this step, OpenAI may be experiencing issues.
Uploading an epub format e-book to the webpage results in an error message at the file name: File: Error: html2text is required to parse Epub files: pip install html2text. After installing pip install html2text, the same error still occurs."
第一次用 docker 求问，docker compose up 以后提示 5000 端口占用，修改端口
但是上传文件失败了
请问这种情况要如何修改
was trying to run the app locally, got this:
followed each step as specified:
cd chatfiles-ui npm install npm run dev cd chatfiles python3 server.py
my OS is Ubuntu 20.04
Can it support multiple OPENAIs_ API_ Load balancing between KEY?
能否支持在多个 OPENAI_API_KEY 之间负载均衡?
Possible steps:
SidebarSettings entry in UI for python endpoint/authenticationIn this way no secondary UI container is needed and we can deploy on one container to use this project (even deploy to managed docker hoster like fly.io)
A small issue: "Index file does not exist" when delete the conservation and reload the same pdf file.
This might be solve via:
In "query_from_llama_index", replace
index_name = get_index_name_with_json_extension(index_name)
with,
index_name = get_index_name_with_json_extension(os.path.splitext(index_name)[0])
感谢您优秀的项目！
Unexpected token '<', "<!DOCTYPE "... is not valid JSON.
在上传文件后，在前端出现这个错误，不知道如何解决
多文件还没有支持吗？
RTRT
File: Error: The constructor now takes in a list of Node objects. Since you are passing in a list of Document objects, please use from_documents instead.
after I uploaded a PDF file,I got this. any help? thanks!
上传pdf或epub文件时，页面提示如下：错误
Error
Unexpected token '<', " <h"... is not valid JSON.
《斯坦福高效睡眠法》.pdf
已经在文件中设置了代理域名，docker中启动为什么访问还会报错呢？本地启动就没问题。很是奇怪。
export const OPENAI_API_HOST =
process.env.OPENAI_API_HOST || 'balabala.xyz';
chatfiles-ui | [TypeError: fetch failed] {
chatfiles-ui | cause: [Error: Client network socket disconnected before secure TLS connection was established] {
chatfiles-ui | code: 'ECONNRESET',
chatfiles-ui | path: undefined,
chatfiles-ui | host: 'api.openai.com',
chatfiles-ui | port: 443,
chatfiles-ui | localAddress: undefined
mac13.2.1 (22D68)
No matter how I upload the file, restart the service, rebuild the docker container, it always responds to me: Index file does not exist.
Got this error when uploading the a file after successfully running the docker-compose
2023-04-25 18:37:07 chatfiles-ui | FetchError: request to http://127.0.0.1:5000/upload failed, reason: connect ECONNREFUSED 127.0.0.1:5000 2023-04-25 18:37:07 chatfiles-ui | at ClientRequest.<anonymous> (file:///app/node_modules/node-fetch/src/index.js:108:11) 2023-04-25 18:37:07 chatfiles-ui | at ClientRequest.emit (node:events:525:35) 2023-04-25 18:37:07 chatfiles-ui | at Socket.socketErrorListener (node:_http_client:495:9) 2023-04-25 18:37:07 chatfiles-ui | at Socket.emit (node:events:513:28) 2023-04-25 18:37:07 chatfiles-ui | at emitErrorNT (node:internal/streams/destroy:151:8) 2023-04-25 18:37:07 chatfiles-ui | at emitErrorCloseNT (node:internal/streams/destroy:116:3) 2023-04-25 18:37:07 chatfiles-ui | at process.processTicksAndRejections (node:internal/process/task_queues:82:21) { 2023-04-25 18:37:07 chatfiles-ui | type: 'system', 2023-04-25 18:37:07 chatfiles-ui | errno: 'ECONNREFUSED', 2023-04-25 18:37:07 chatfiles-ui | code: 'ECONNREFUSED', 2023-04-25 18:37:07 chatfiles-ui | erroredSysCall: 'connect'
Could you make it support Azure OpenAI API?
2023-04-17 10:06:55 chatfiles | Token indices sequence length is longer than the specified maximum sequence length for this model (3390 > 1024). Running this sequence through the model will result in indexing errors
2023-04-17 10:06:58 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens
2023-04-17 10:06:58 chatfiles | INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 10086 tokens
2023-04-17 10:06:58 chatfiles | INFO:werkzeug:172.18.0.2 - - [17/Apr/2023 02:06:58] "POST /upload HTTP/1.1" 200 -
chatfiles | standard_init_linux.go:211: exec user process caused "exec format error"
chatfiles-ui | standard_init_linux.go:211: exec user process caused "exec format error"
能否提供一下Dockerfile?想看一下构建依赖
請問文件上傳后會保存在哪個文件夾？
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.