search

svilupp / PromptingTools.jl

Streamline your life using PromptingTools.jl, the Julia package that simplifies interacting with large language models.
https://svilupp.github.io/PromptingTools.jl/dev/
MIT License
96 stars 9 forks source link

Unable to get started #132

Closed KronosTheLate closed 2 months ago

KronosTheLate commented 2 months ago

Following the getting started page, I have done the following: 1) Add my Open AI API key to the global ENV dictionary in my startup.jl 2) Install PromtingTools 3) Run ai"Hello!"

This results in the following error:

julia> ai"Hello!"
ERROR: ArgumentError: api_key cannot be empty
Stacktrace:
  [1] auth_header(::OpenAI.OpenAIProvider, api_key::String)
    @ OpenAI ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:40
  [2] _request(api::String, provider::OpenAI.OpenAIProvider, api_key::String; method::String, query::Nothing, http_kwargs::@NamedTuple{…}, streamcallback::Nothing, additional_headers::Vector{…}, kwargs::@Kwargs{…})
    @ OpenAI ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:159
  [3] _request
    @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:141 [inlined]
  [4] #openai_request#14
    @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:205 [inlined]
  [5] openai_request
    @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:198 [inlined]
  [6] #create_chat#19
    @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:368 [inlined]
  [7] create_chat
    @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:362 [inlined]
  [8] #create_chat#162
    @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:86 [inlined]
  [9] create_chat
    @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:81 [inlined]
 [10] macro expansion
    @ ./timing.jl:395 [inlined]
 [11] aigenerate(prompt_schema::PromptingTools.OpenAISchema, prompt::String; verbose::Bool, api_key::String, model::String, return_all::Bool, dry_run::Bool, conversation::Vector{…}, http_kwargs::@NamedTuple{…}, api_kwargs::@NamedTuple{}, kwargs::@Kwargs{})
    @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:495
 [12] aigenerate(prompt::String; model::String, kwargs::@Kwargs{return_all::Bool})
    @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_interface.jl:297
 [13] macro expansion
    @ ~/.julia/packages/PromptingTools/wSKVR/src/macros.jl:39 [inlined]
 [14] top-level scope
    @ REPL[8]:1
Some type information was truncated. Use `show(err)` to see complete types.

Despite the fact that the environment variable is set:

julia> haskey(ENV, "OPENAI_API_KEY")
true

Have I done something wrong, or should it be working at this point? I could use some help figuring out what I am missing to get things working...

Versions:

Julia Version 1.10.2
 [670122d1] PromptingTools v0.19.0
svilupp commented 2 months ago

Would you mind starting a temp environment and running it again? Make sure that you can see the ENV["OPENAI_API_KEY"] and that there is no typo, before you import the package.

That's the most common mistake.

An easy check if the package loaded it correctly is if it shows up in PromptingTools.OPENAI_API_KEY.

There was a bug in past versions where people started the package before they set the ENV and Julia was for whatever reason precompiling the get(ENV..) call as well, so the only solution was to get rid of the cache (precompile again, upgrade version, manually delete the cache) - see the FAQ note.

But nowadays I split the get(ENV,..) in two steps to prevent Julia from inlining/precompiling it. No one has reported the issue since that fix.

KronosTheLate commented 2 months ago

I am not getting a different error message, which states that I have exceeded my current quota. I assumed that since I can use ChatGPT in the browser, I could also make requests via this interface for free. Is that wrong?

Full stacktrace of new error ``` julia> ai"Hello!" ERROR: HTTP.Exceptions.StatusError(429, "POST", "/v1/chat/completions", HTTP.Messages.Response: """ HTTP/1.1 429 Too Many Requests Date: Mon, 15 Apr 2024 06:44:21 GMT Content-Type: application/json; charset=utf-8 Content-Length: 337 Connection: keep-alive vary: Origin x-request-id: req_47fc080729878fd0ef899db83bb08b55 strict-transport-security: max-age=15724800; includeSubDomains CF-Cache-Status: DYNAMIC Set-Cookie: ****** Set-Cookie: ****** Server: cloudflare CF-RAY: 8749f76edc4aabd5-CPH alt-svc: h3=":443"; ma=86400 { "error": { "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.", "type": "insufficient_quota", "param": null, "code": "insufficient_quota" } } """) Stacktrace: [1] (::HTTP.ConnectionRequest.var"#connections#4"{…})(req::HTTP.Messages.Request; proxy::Nothing, socket_type::Type, socket_type_tls::Type, readtimeout::Int64, connect_timeout::Int64, logerrors::Bool, logtag::Nothing, kw::@Kwargs{…}) @ HTTP.ConnectionRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/ConnectionRequest.jl:141 [2] (::Base.var"#96#98"{…})(args::HTTP.Messages.Request; kwargs::@Kwargs{…}) @ Base ./error.jl:308 [3] (::HTTP.RetryRequest.var"#manageretries#3"{…})(req::HTTP.Messages.Request; retry::Bool, retries::Int64, retry_delays::ExponentialBackOff, retry_check::Function, retry_non_idempotent::Bool, kw::@Kwargs{…}) @ HTTP.RetryRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RetryRequest.jl:75 [4] manageretries @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RetryRequest.jl:30 [inlined] [5] (::HTTP.CookieRequest.var"#managecookies#4"{…})(req::HTTP.Messages.Request; cookies::Bool, cookiejar::HTTP.Cookies.CookieJar, kw::@Kwargs{…}) @ HTTP.CookieRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/CookieRequest.jl:42 [6] managecookies @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/CookieRequest.jl:19 [inlined] [7] (::HTTP.HeadersRequest.var"#defaultheaders#2"{…})(req::HTTP.Messages.Request; iofunction::Nothing, decompress::Nothing, basicauth::Bool, detect_content_type::Bool, canonicalize_headers::Bool, kw::@Kwargs{…}) @ HTTP.HeadersRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/HeadersRequest.jl:71 [8] defaultheaders @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/HeadersRequest.jl:14 [inlined] [9] (::HTTP.RedirectRequest.var"#redirects#3"{…})(req::HTTP.Messages.Request; redirect::Bool, redirect_limit::Int64, redirect_method::Nothing, forwardheaders::Bool, response_stream::Nothing, kw::@Kwargs{…}) @ HTTP.RedirectRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RedirectRequest.jl:25 [10] redirects @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RedirectRequest.jl:14 [inlined] [11] (::HTTP.MessageRequest.var"#makerequest#3"{…})(method::String, url::URIs.URI, headers::Vector{…}, body::IOBuffer; copyheaders::Bool, response_stream::Nothing, http_version::HTTP.Strings.HTTPVersion, verbose::Int64, kw::@Kwargs{…}) @ HTTP.MessageRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/MessageRequest.jl:35 [12] makerequest @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/MessageRequest.jl:24 [inlined] [13] request(stack::HTTP.MessageRequest.var"#makerequest#3"{…}, method::String, url::String, h::Vector{…}, b::IOBuffer, q::Vector{…}; headers::Vector{…}, body::IOBuffer, query::Vector{…}, kw::@Kwargs{…}) @ HTTP ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:457 [14] #request#20 @ ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:315 [inlined] [15] request (repeats 2 times) @ ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:313 [inlined] [16] #request_body#3 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:82 [inlined] [17] request_body @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:78 [inlined] [18] _request(api::String, provider::OpenAI.OpenAIProvider, api_key::String; method::String, query::Nothing, http_kwargs::@NamedTuple{…}, streamcallback::Nothing, additional_headers::Vector{…}, kwargs::@Kwargs{…}) @ OpenAI ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:162 [19] _request @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:141 [inlined] [20] #openai_request#14 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:205 [inlined] [21] openai_request @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:198 [inlined] [22] #create_chat#19 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:368 [inlined] [23] create_chat @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:362 [inlined] [24] #create_chat#162 @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:86 [inlined] [25] create_chat @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:81 [inlined] [26] macro expansion @ ./timing.jl:395 [inlined] [27] aigenerate(prompt_schema::PromptingTools.OpenAISchema, prompt::String; verbose::Bool, api_key::String, model::String, return_all::Bool, dry_run::Bool, conversation::Vector{…}, http_kwargs::@NamedTuple{…}, api_kwargs::@NamedTuple{}, kwargs::@Kwargs{}) @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:495 [28] aigenerate(prompt::String; model::String, kwargs::@Kwargs{return_all::Bool}) @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_interface.jl:297 [29] macro expansion @ ~/.julia/packages/PromptingTools/wSKVR/src/macros.jl:39 [inlined] [30] top-level scope @ REPL[2]:1 caused by: HTTP.Exceptions.StatusError(429, "POST", "/v1/chat/completions", HTTP.Messages.Response: """ HTTP/1.1 429 Too Many Requests Date: Mon, 15 Apr 2024 06:44:21 GMT Content-Type: application/json; charset=utf-8 Content-Length: 337 Connection: keep-alive vary: Origin x-request-id: req_47fc080729878fd0ef899db83bb08b55 strict-transport-security: max-age=15724800; includeSubDomains CF-Cache-Status: DYNAMIC Set-Cookie: ****** Set-Cookie: ****** Server: cloudflare CF-RAY: 8749f76edc4aabd5-CPH alt-svc: h3=":443"; ma=86400 { "error": { "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.", "type": "insufficient_quota", "param": null, "code": "insufficient_quota" } } """) Stacktrace: [1] (::HTTP.ExceptionRequest.var"#exceptions#2"{…})(stream::HTTP.Streams.Stream{…}; status_exception::Bool, timedout::ConcurrentUtilities.TimedOut{…}, logerrors::Bool, logtag::Nothing, kw::@Kwargs{…}) @ HTTP.ExceptionRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/ExceptionRequest.jl:19 [2] exceptions @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/ExceptionRequest.jl:13 [inlined] [3] #2 @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/TimeoutRequest.jl:22 [inlined] [4] macro expansion @ ~/.julia/packages/ConcurrentUtilities/J6iMP/src/try_with_timeout.jl:82 [inlined] [5] (::ConcurrentUtilities.var"#2#4"{HTTP.Messages.Response, Timer, ConcurrentUtilities.TimedOut{…}, Channel{…}, HTTP.TimeoutRequest.var"#2#5"{…}})() @ ConcurrentUtilities ~/.julia/packages/ConcurrentUtilities/J6iMP/src/ConcurrentUtilities.jl:9 Stacktrace: [1] try_yieldto(undo::typeof(Base.ensure_rescheduled)) @ Base ./task.jl:931 [2] wait() @ Base ./task.jl:995 [3] wait(c::Base.GenericCondition{ReentrantLock}; first::Bool) @ Base ./condition.jl:130 [4] wait @ ./condition.jl:125 [inlined] [5] take_unbuffered(c::Channel{HTTP.Messages.Response}) @ Base ./channels.jl:494 [6] take! @ ./channels.jl:471 [inlined] [7] try_with_timeout(f::Function, timeout::Int64, ::Type{HTTP.Messages.Response}) @ ConcurrentUtilities ~/.julia/packages/ConcurrentUtilities/J6iMP/src/try_with_timeout.jl:89 [8] (::HTTP.TimeoutRequest.var"#timeouts#3"{…})(stream::HTTP.Streams.Stream{…}; readtimeout::Int64, logerrors::Bool, logtag::Nothing, kw::@Kwargs{…}) @ HTTP.TimeoutRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/TimeoutRequest.jl:21 [9] (::HTTP.ConnectionRequest.var"#connections#4"{…})(req::HTTP.Messages.Request; proxy::Nothing, socket_type::Type, socket_type_tls::Type, readtimeout::Int64, connect_timeout::Int64, logerrors::Bool, logtag::Nothing, kw::@Kwargs{…}) @ HTTP.ConnectionRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/ConnectionRequest.jl:119 [10] (::Base.var"#96#98"{…})(args::HTTP.Messages.Request; kwargs::@Kwargs{…}) @ Base ./error.jl:308 [11] (::HTTP.RetryRequest.var"#manageretries#3"{…})(req::HTTP.Messages.Request; retry::Bool, retries::Int64, retry_delays::ExponentialBackOff, retry_check::Function, retry_non_idempotent::Bool, kw::@Kwargs{…}) @ HTTP.RetryRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RetryRequest.jl:75 [12] manageretries @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RetryRequest.jl:30 [inlined] [13] (::HTTP.CookieRequest.var"#managecookies#4"{…})(req::HTTP.Messages.Request; cookies::Bool, cookiejar::HTTP.Cookies.CookieJar, kw::@Kwargs{…}) @ HTTP.CookieRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/CookieRequest.jl:42 [14] managecookies @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/CookieRequest.jl:19 [inlined] [15] (::HTTP.HeadersRequest.var"#defaultheaders#2"{…})(req::HTTP.Messages.Request; iofunction::Nothing, decompress::Nothing, basicauth::Bool, detect_content_type::Bool, canonicalize_headers::Bool, kw::@Kwargs{…}) @ HTTP.HeadersRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/HeadersRequest.jl:71 [16] defaultheaders @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/HeadersRequest.jl:14 [inlined] [17] (::HTTP.RedirectRequest.var"#redirects#3"{…})(req::HTTP.Messages.Request; redirect::Bool, redirect_limit::Int64, redirect_method::Nothing, forwardheaders::Bool, response_stream::Nothing, kw::@Kwargs{…}) @ HTTP.RedirectRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RedirectRequest.jl:25 [18] redirects @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/RedirectRequest.jl:14 [inlined] [19] (::HTTP.MessageRequest.var"#makerequest#3"{…})(method::String, url::URIs.URI, headers::Vector{…}, body::IOBuffer; copyheaders::Bool, response_stream::Nothing, http_version::HTTP.Strings.HTTPVersion, verbose::Int64, kw::@Kwargs{…}) @ HTTP.MessageRequest ~/.julia/packages/HTTP/vnQzp/src/clientlayers/MessageRequest.jl:35 [20] makerequest @ ~/.julia/packages/HTTP/vnQzp/src/clientlayers/MessageRequest.jl:24 [inlined] [21] request(stack::HTTP.MessageRequest.var"#makerequest#3"{…}, method::String, url::String, h::Vector{…}, b::IOBuffer, q::Vector{…}; headers::Vector{…}, body::IOBuffer, query::Vector{…}, kw::@Kwargs{…}) @ HTTP ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:457 [22] #request#20 @ ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:315 [inlined] [23] request (repeats 2 times) @ ~/.julia/packages/HTTP/vnQzp/src/HTTP.jl:313 [inlined] [24] #request_body#3 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:82 [inlined] [25] request_body @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:78 [inlined] [26] _request(api::String, provider::OpenAI.OpenAIProvider, api_key::String; method::String, query::Nothing, http_kwargs::@NamedTuple{…}, streamcallback::Nothing, additional_headers::Vector{…}, kwargs::@Kwargs{…}) @ OpenAI ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:162 [27] _request @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:141 [inlined] [28] #openai_request#14 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:205 [inlined] [29] openai_request @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:198 [inlined] [30] #create_chat#19 @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:368 [inlined] [31] create_chat @ ~/.julia/packages/OpenAI/d65zV/src/OpenAI.jl:362 [inlined] [32] #create_chat#162 @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:86 [inlined] [33] create_chat @ ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:81 [inlined] [34] macro expansion @ ./timing.jl:395 [inlined] [35] aigenerate(prompt_schema::PromptingTools.OpenAISchema, prompt::String; verbose::Bool, api_key::String, model::String, return_all::Bool, dry_run::Bool, conversation::Vector{…}, http_kwargs::@NamedTuple{…}, api_kwargs::@NamedTuple{}, kwargs::@Kwargs{}) @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_openai.jl:495 [36] aigenerate(prompt::String; model::String, kwargs::@Kwargs{return_all::Bool}) @ PromptingTools ~/.julia/packages/PromptingTools/wSKVR/src/llm_interface.jl:297 [37] macro expansion @ ~/.julia/packages/PromptingTools/wSKVR/src/macros.jl:39 [inlined] [38] top-level scope @ REPL[2]:1 ```
svilupp commented 2 months ago

Ah, good! That means that the api key issue is gone. Which of the steps above resolved it for you?

On your current error, it's common for new / non-paying users. It's very similar to this error: https://siml.earth/PromptingTools.jl/dev/frequently_asked_questions#Getting-an-error-%22Rate-limit-exceeded%22-from-OpenAI?

But it's likely because you don't have any prepaid credit in your OpenAI account.

I'd suggest prepaying $5 credit: https://help.openai.com/en/articles/8264644-what-is-prepaid-billing

KronosTheLate commented 2 months ago

I can use chat.openai.com/ freely. Are the rules different when accessed through this package? I just assumed that as long as I kept to normal usage and only the free models, I did not have to whip out a credit card...

KronosTheLate commented 2 months ago

Looking at the billing information with OpenAI, I can see the following: image

Which makes it clear that my chatGPT account is not reflected by that information, indicating that the two accounts have separate statuses. That helps explain why I can freely make requests online, but not via the OpenAI API. I do not plan on paying for this when I can freely use the online service.

To keep this confusion from happening again, perhaps the getting started section could mention that you have to pay to get started?