Closed yaya6630170 closed 11 months ago
error [Error: Network Error] { config: { transitional: { silentJSONParsing: true, forcedJSONParsing: true, clarifyTimeoutError: false }, adapter: [AsyncFunction: fetchAdapter], transformRequest: [ [Function: transformRequest] ], transformResponse: [ [Function: transformResponse] ], timeout: 0, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: { Accept: 'application/json, text/plain, /', 'Content-Type': 'application/json', 'User-Agent': 'OpenAI/NodeJS/3.2.1', Authorization: 'Bearer sk-XXXXX'(here is the openai api key) }, method: 'post',
url: 'https://api.openai.com/v1/embeddings' }, code: 'ERR_NETWORK', request: Request { [Symbol(realm)]: { settingsObject: [Object] },
method: 'POST',
localURLsOnly: false,
unsafeRequest: false,
body: [Object],
client: [Object],
reservedClient: null,
replacesClientId: '',
window: 'client',
keepalive: false,
serviceWorkers: 'all',
initiator: '',
destination: '',
priority: null,
origin: 'client',
policyContainer: 'client',
referrer: 'client',
referrerPolicy: '',
mode: 'cors',
useCORSPreflightFlag: false,
credentials: 'same-origin',
useCredentials: false,
cache: 'default',
redirect: 'follow',
integrity: '',
cryptoGraphicsNonceMetadata: '',
parserMetadata: '',
reloadNavigation: false,
historyNavigation: false,
userActivation: false,
taintedOrigin: false,
redirectCount: 0,
responseTainting: 'basic',
preventNoCacheCacheControlHeaderModification: false,
done: false,
timingAllowFailed: false,
headersList: [HeadersList],
urlList: [Array],
url: [URL]
},
[Symbol(signal)]: AbortSignal { aborted: false },
[Symbol(headers)]: HeadersList {
cookies: null,
[Symbol(headers map)]: [Map],
[Symbol(headers map sorted)]: null
}
}, response: undefined, isAxiosError: true, toJSON: [Function: toJSON] } d:\Documents\GitHub\gpt4-pdf-chatbot-langchain\scripts\ingest-data.ts:53 throw new Error('Failed to ingest your data'); ^
[Error: Failed to ingest your data]
Node.js v18.14.2 ELIFECYCLE Command failed with exit code 1.
fixed it already. thanks
@TextToSQL how did you fix it?
i 've spent hours 1) trying to understand where the problem is, 2) consulting with chat gpt :-) , and 3) tailoring the code here and there. i 've also updated several packages. to be very honest, i am not 100 % sure what helped exactly. as a first step, i 'd recommend you install VS studio , take a look at problems tab (it would say in which part of the code there is an issue), make sure to install all packages as per Mayo instructions. I think most important is to make sure PineCone client is up to date. I hope this helps.
sorry, another first step is to look at the console and see if the text is actually splitting and embedding works. if yes, than the issue is likely with pinecone client
another one i forgot to mention - make sure to change the gpt model if you don't have access to gpt4 yet. i've changed mine to gpt3.5turbo
@TextToSQL thx! I have a very strange "PineconeClient: Project name not set. Call init() first." error, despite the official doc no requiring it.
i thought we are initializing it somewhere. my best advice - ask chatgpt about this particular error. and also look at the 'problems' tab in VS
did pinecone-client install ok?
The error is know, but none of the fix work for me (updating node, pining lib to 0.0.10)
https://github.com/pinecone-io/pinecone-ts-client/issues/12
EDIT: I managed to get a new error by adding the projectName directly on the object
EDIT2: new error
So I finally managed to make it work.
The pinecode lib use the projectName to build the url, so you have to set on the object. The projectName can be found in the pinecode web UI.
// Pinecode lib
// Pinecode interface with name
// Your code where you set the projectName
I have no idea why it works for everyone else.
another one i forgot to mention - make sure to change the gpt model if you don't have access to gpt4 yet. i've changed mine to gpt3.5turbo
This is a major cause of issues. Many people attempt to use gpt-4 when they don't yet have access.
So I finally managed to make it work.
The pinecode lib use the projectName to build the url, but so you have to set on the object. The projectName can be found in the pinecode web UI.
// Pinecode lib // Pinecode interface with name // Your code where you set the projectName
I have no idea why it works for everyone else.
strange why it doesn't work for you without setting a projectname.
另一个我忘记提到的 - 如果您还没有访问 gpt4,请确保更改 gpt 模型。我已经把我的改成了 gpt3.5turbo
这是造成问题的主要原因。许多人在还没有访问权限时尝试使用 gpt-4。
已经是gpt3.5turbo了 T T文本也在分段,确实不明白是什么问题,pinecode需要修改么?我看他们上面提到了pinecone-client,是需要装这个?
So I finally managed to make it work.
The pinecode lib use the projectName to build the url, so you have to set on the object. The projectName can be found in the pinecode web UI.
// Pinecode lib // Pinecode interface with name // Your code where you set the projectName
I have no idea why it works for everyone else.
Awesome thanks for this solution I was also experiencing this, adding the pinecone.projectName to the initPinectode function got me to the next problem, that was causing by the basePath in the pinecone library, the concat didn't work for my url so I just hardcoded and it worked.
error [Error: Network Error] { config: { transitional: { silentJSONParsing: true, forcedJSONParsing: true, clarifyTimeoutError: false }, adapter: [AsyncFunction: fetchAdapter], transformRequest: [ [Function: transformRequest] ], transformResponse: [ [Function: transformResponse] ], timeout: 0, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: { Accept: 'application/json, text/plain, /', 'Content-Type': 'application/json', 'User-Agent': 'OpenAI/NodeJS/3.2.1', Authorization: 'Bearer sk-XXXXX'(here is the openai api key) }, method: 'post',
url: 'https://api.openai.com/v1/embeddings' }, code: 'ERR_NETWORK', request: Request { [Symbol(realm)]: { settingsObject: [Object] }, [Symbol(state)]: { method: 'POST', localURLsOnly: false, unsafeRequest: false, body: [Object], client: [Object], reservedClient: null, replacesClientId: '', window: 'client', keepalive: false, serviceWorkers: 'all', initiator: '', destination: '', priority: null, origin: 'client', policyContainer: 'client', referrer: 'client', referrerPolicy: '', mode: 'cors', useCORSPreflightFlag: false, credentials: 'same-origin', useCredentials: false, cache: 'default', redirect: 'follow', integrity: '', cryptoGraphicsNonceMetadata: '', parserMetadata: '', reloadNavigation: false, historyNavigation: false, userActivation: false, taintedOrigin: false, redirectCount: 0, responseTainting: 'basic', preventNoCacheCacheControlHeaderModification: false, done: false, timingAllowFailed: false, headersList: [HeadersList], urlList: [Array], url: [URL] }, [Symbol(signal)]: AbortSignal { aborted: false }, [Symbol(headers)]: HeadersList { cookies: null, [Symbol(headers map)]: [Map], [Symbol(headers map sorted)]: null } }, response: undefined, isAxiosError: true, toJSON: [Function: toJSON] } d:\Documents\GitHub\gpt4-pdf-chatbot-langchain\scripts\ingest-data.ts:53 throw new Error('Failed to ingest your data'); ^
[Error: Failed to ingest your data]
Node.js v18.14.2 ELIFECYCLE Command failed with exit code 1.
Exact same problem here. Keep getting the Network Error message. But I have Clash proxy running at the same time, not sure if the Clash casues network conflicts.
I tried to change Clash proxy mode to Global、Rule、Direct multiple times, and the Network Error message keeps appearing.
I tried to change Clash proxy mode to Global、Rule、Direct multiple times, and the Network Error message keeps appearing.
Me, too, damn
I met a similar problem about Failed to ingest your data
, but the original error is fromerror [Error: Network Error]
after creating vector store...
I promise the proxy setting is right(both for bash and npm)
Problem solved. For those who use Clash and VS code the same time, do the following to check the results. I am not sure which step is necessary, but it works for me anyway.
另一个我忘记提到的 - 如果您还没有访问 gpt4,请确保更改 gpt 模型。我已经把我的改成了 gpt3.5turbo
这是造成问题的主要原因。许多人在还没有访问权限时尝试使用 gpt-4。
已经是gpt3.5turbo了 T T文本也在分段,确实不明白是什么问题,pinecode需要修改么?我看他们上面提到了pinecone-client,是需要装这个?
如果用Clash科学上网的话,可以看下我的回复
Problem solved. For those who use Clash and VS code the same time, do the following to check the results. I am not sure which step is necessary, but it works for me anyway.
- Add pinecone.projectName to your file.
- Turn on the Clash TUN mode.
- Change Clash to Global, make sure the proxy address has access to the openai website.
- Final pinecone website result:
网上看到过设置tun mode的,我设置后节点列表就不见了,需要重新卸载掉service mode才可以 设置tun mode的方法也是千奇百怪。。。
另一个我忘记提到的 - 如果您还没有访问 gpt4,请确保更改 gpt 模型。我已经把我的改成了 gpt3.5turbo
这是造成问题的主要原因。许多人在还没有访问权限时尝试使用 gpt-4。
已经是gpt3.5turbo了 T T文本也在分段,确实不明白是什么问题,pinecode需要修改么?我看他们上面提到了pinecone-client,是需要装这个?
如果用Clash科学上网的话,可以看下我的回复
awsome, seems i can get to pinecone, but new problem~~~~creating vector store... error [TypeError: documents.map is not a function] d:\Documents\GitHub\gpt4-pdf-chatbot-langchain\scripts\ingest-data.ts:44 throw new Error('Failed to ingest your data'); ^
[Error: Failed to ingest your data]
我也遇到这个问题,也有科学上网了,但是不行,显然pinecone那边也没办法读入数据,有解决的话麻烦说一下
这我就不清楚了,我是直接把TUN mode开关打开就行了。然后把UWP loopback里能选的都选上了。
另一个我忘记提到的 - 如果您还没有访问 gpt4,请确保更改 gpt 模型。我已经把我的改成了 gpt3.5turbo
这是造成问题的主要原因。许多人在还没有访问权限时尝试使用 gpt-4。
已经是gpt3.5turbo了 T T文本也在分段,确实不明白是什么问题,pinecode需要修改么?我看他们上面提到了pinecone-client,是需要装这个?
如果用Clash科学上网的话,可以看下我的回复
awsome, seems i can get to pinecone, but new problem~~~~creating vector store... error [TypeError: documents.map is not a function] d:\Documents\GitHub\gpt4-pdf-chatbot-langchain\scripts\ingest-data.ts:44 throw new Error('Failed to ingest your data'); ^
[Error: Failed to ingest your data]
试试安装pico-client?
另一个我忘记提到的 - 如果您还没有访问 gpt4,请确保更改 gpt 模型。我已经把我的改成了 gpt3.5turbo
这是造成问题的主要原因。许多人在还没有访问权限时尝试使用 gpt-4。
已经是gpt3.5turbo了 T T文本也在分段,确实不明白是什么问题,pinecode需要修改么?我看他们上面提到了pinecone-client,是需要装这个?
如果用Clash科学上网的话,可以看下我的回复
awsome, seems i can get to pinecone, but new problem~~~~creating vector store... error [TypeError: documents.map is not a function] d:\Documents\GitHub\gpt4-pdf-chatbot-langchain\scripts\ingest-data.ts:44 throw new Error('Failed to ingest your data'); ^
[Error: Failed to ingest your data]
试试安装pico-client?
So I finally managed to make it work. The pinecode lib use the projectName to build the url, but so you have to set on the object. The projectName can be found in the pinecode web UI. // Pinecode lib // Pinecode interface with name // Your code where you set the projectName I have no idea why it works for everyone else.
strange why it doesn't work for you without setting a projectname.
I addded the project name and am getting this error still
I am facing similar problem; after running npm run ingest
and get a successful message, I checked Pinecone index info and got a namespace "books" with a total vectors of 309. However, after initializing the app pnpm run dev
and typing a question, I see the error below in the logs and in the client page an empty response.
PineconeClient: Error getting project name: TypeError: fetch failed
error - [Error: PineconeClient: Project name not set. Call init() first.] {
page: '/api/chat'
}
wait - compiling /_error (client and server)...
Pinecode and config files are matching README instructions.
same error for me...
initPinectode
thanks, I did this but now I get a new error :( Error: PineconeClient: Error calling upsertRaw: FetchError: The request failed and the interceptors did not return an alternative response]
Is anyone else getting status code 429 aka "too many requests"?
Is anyone else getting status code 429 aka "too many requests"?
you can use python chatgpt api demo to check your problem. I fix this issue by setting up a payment method in my openai api page.
With regard to the 429. Check out here.
The reason was that I created my API key BEFORE converting my OpenAI account to paid (adding credit card). Doesn't matter if you only upgrade, you also need to create a new api key entirely. I created another API key AFTER I added my credit card and it worked fine!
This helped me as well
I am getting the same error. Any insights?
request: Request { [Symbol(realm)]: { settingsObject: [Object] },
method: 'POST',
localURLsOnly: false,
unsafeRequest: false,
body: [Object],
client: [Object],
reservedClient: null,
replacesClientId: '',
window: 'client',
keepalive: false,
serviceWorkers: 'all',
initiator: '',
destination: '',
priority: null,
origin: 'client',
policyContainer: 'client',
referrer: 'client',
referrerPolicy: '',
mode: 'cors',
useCORSPreflightFlag: false,
credentials: 'same-origin',
useCredentials: false,
cache: 'default',
redirect: 'follow',
integrity: '',
cryptoGraphicsNonceMetadata: '',
parserMetadata: '',
reloadNavigation: false,
historyNavigation: false,
userActivation: false,
taintedOrigin: false,
redirectCount: 0,
responseTainting: 'basic',
preventNoCacheCacheControlHeaderModification: false,
done: false,
timingAllowFailed: false,
headersList: [HeadersList],
urlList: [Array],
url: [URL]
},
[Symbol(signal)]: AbortSignal { aborted: false },
[Symbol(headers)]: HeadersList {
cookies: null,
[Symbol(headers map)]: [Map],
[Symbol(headers map sorted)]: null
}
}, response: { ok: false, status: 401, statusText: 'Unauthorized', headers: HeadersList { cookies: null,
[Symbol(headers map sorted)]: null
},
config: {
transitional: [Object],
adapter: [AsyncFunction: fetchAdapter],
transformRequest: [Array],
transformResponse: [Array],
timeout: 0,
xsrfCookieName: 'XSRF-TOKEN',
xsrfHeaderName: 'X-XSRF-TOKEN',
maxContentLength: -1,
maxBodyLength: -1,
validateStatus: [Function: validateStatus],
headers: [Object],
method: 'post',
Hi, @yaya6630170! I'm Dosu, and I'm helping the gpt4-pdf-chatbot-langchain team manage their backlog. I wanted to let you know that we are marking this issue as stale.
From what I understand, you opened the issue titled "Error: Failed to ingest your data" because you were experiencing an error while trying to extract code from a PDF. Other users have provided suggestions and solutions, such as updating packages, installing VS Studio, and setting the projectName in the pinecone library. There was also a discussion about receiving a status code 429 (too many requests), with suggestions to check the OpenAI API key and payment method.
Before we close this issue, we wanted to check if it is still relevant to the latest version of the gpt4-pdf-chatbot-langchain repository. If it is, please let us know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.
Thank you for your understanding, and please don't hesitate to reach out if you have any further questions or concerns.
Hi, @yaya6630170! I'm Dosu, and I'm helping the gpt4-pdf-chatbot-langchain team manage their backlog. I wanted to let you know that we are marking this issue as stale.
From what I understand, you opened the issue titled "Error: Failed to ingest your data" because you were experiencing an error while trying to extract code from a PDF. Other users have provided suggestions and solutions, such as updating packages, installing VS Studio, and setting the projectName in the pinecone library. There was also a discussion about receiving a status code 429 (too many requests), with suggestions to check the OpenAI API key and payment method.
Before we close this issue, we wanted to check if it is still relevant to the latest version of the gpt4-pdf-chatbot-langchain repository. If it is, please let us know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.
Thank you for your understanding, and please don't hesitate to reach out if you have any further questions or concerns.
I extracted parts of the code except for the pdf content. Please I just can't find the bug.....