From dc130efac63604b1fb8664e64869fe58f22cf62e Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Tue, 5 Sep 2023 09:18:37 -0700
Subject: [PATCH] update streaming docs to show it working for async completion
 calls

---
 docs/my-website/docs/completion/stream.md     |  11 ++++----
 litellm/__pycache__/__init__.cpython-311.pyc  | Bin 7908 -> 7908 bytes
 litellm/__pycache__/main.cpython-311.pyc      | Bin 29129 -> 28982 bytes
 .../__pycache__/supabase.cpython-311.pyc      | Bin 6760 -> 6760 bytes
 litellm/tests/test_streaming.py               |  25 ++++++++++++++++--
 5 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/docs/my-website/docs/completion/stream.md b/docs/my-website/docs/completion/stream.md
index da578f7dee8..6cb813ae934 100644
--- a/docs/my-website/docs/completion/stream.md
+++ b/docs/my-website/docs/completion/stream.md
@@ -34,9 +34,11 @@ print(response)
 
 ## Async Streaming
 We've implemented an `__anext__()` function in the streaming object returned. This enables async iteration over the streaming object. 
+
 ### Usage
+Here's an example of using it with openai. But this 
 ```
-from litellm import acompletion
+from litellm import completion
 import asyncio
 
 def logger_fn(model_call_object: dict):
@@ -46,11 +48,10 @@ def logger_fn(model_call_object: dict):
 user_message = "Hello, how are you?"
 messages = [{"content": user_message, "role": "user"}]
 
-# # test on ai21 completion call
-async def ai21_async_completion_call():
+async def completion_call():
     try:
         response = completion(
-            model="j2-ultra", messages=messages, stream=True, logger_fn=logger_fn
+            model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
         )
         print(f"response: {response}")
         complete_response = ""
@@ -67,5 +68,5 @@ async def ai21_async_completion_call():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-asyncio.run(ai21_async_completion_call())
+asyncio.run(completion_call())
 ```
\ No newline at end of file
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index a95ce65c852fe2b43aaf76a12b70f58f1bfa0917..6c515ddae086113debfde5b6f66eaf2409c0e21f 100644
GIT binary patch
delta 22
ccmaE2`^1)aIWI340}zD!eoxuGk@vbB08|tQhyVZp

delta 22
ccmaE2`^1)aIWI340}$wje@k)L$a`H508o4e>;M1&

diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index d7f053f664c2c135a849439ad735c7af7c343ae0..adb45149c93427b0a44a8cd3be029af9e0f8d8bf 100644
GIT binary patch
delta 1363
zcmY+DdrVtZ9LLY^URuhd0)<k_ySz$Afk{yc;W40v00L^_lnNn*(?OvRxRgy8ge{p)
z6NxduKS<1s7|48VM)4#I*<3b~#mAh0k2v9v8C<5*vB{E+IR8-3>He7~x1aCt@jbtD
zdvESn*Wt`BpnXrPjV63O-Lp&Emb7;8X8H?U1wbgF;4{0-T;qL(ev8WjL?RyZ&>mqI
zizb`|LQe7D!{sXCUY#$+Z*&>`sjgIink&t3by@xCuJrJ{MBXcQ6^G|U4VB>0ykre;
zBpoBJQoI5d*o(X11S?icx!T8R2CtXVOimm6BxhndHSzcfn#1`d&E>3Mm!x*kME1GI
zJRwhjrAKVYnosfxnIj><nLHyVYqDXARcPjb%UaZV38rv1_FuTkX0;!ST1{Lhz#yBA
z|DLy)JMj=e1KUWNli?s6P0<6~V#kdZfc<PKRsV2zDsH78=5u;7dSRWN&#32f(49EO
zl&lVb4z`j#4e$o5%SixGvuAP*k}L-vu;KjM021pmrvZd;ywDAec$HJfDlIYqV$Gf*
zJeN}%(>P^1-FT9}l~d6OMK8lB9xpP<N+<&BW0UYgkt$|v+Cf#6_*~OYyqj<2<Fa(M
z8cL=dbetZ<QmbBe&cBH60=?ETWv1g(gdRE}pMD9w*2>7R=Y)jc#wFrs)&iJ7cTyE*
z6t}=64iwkJVf>)j1k>#6Vj8VdjQriA-EP4-`&o!(&sI)GKofpb^9Ou^%e5x;72a1?
z@#k7w_IEtol=_3pk0OW*1qVE#L66ew_Vx~YCX@{<tFsl}5dQatA!@)A@F?z3P*Hvr
z#g7Dj=NN0^z<28!ajVXtKWZT42)Vx>NUZKP`|I{2jvc9yY4<hjBQ+#5|A&lHe6uyx
zko!}5?v6et^Rc^x<DS5)9rsh%!gCK`rnQ_bwq(|Gxhy-hLRS;a9hGF&4&kISy0cnd
zlgm3R<h2Twh^q@kV?DR2TIkj6CX>)>l9LF%E;l3zy^+$AEc8yPvsCE4tOkwH-NM!c
zp)32U8hKE}BS&mQez??B<_I6U(pnx}-=>#WT5EOnZSnF-TfB<r*gjyuo)@l3{}8O{
zvZ*BgdD+-_*IyE}VxW7k`b+VcKF7uGNl;@}k3*&7jw&|T^Ojn>BzjdG7M*ei<7iIu
zGEX+6oc=x!rQX1Ra#lDPHq%V~ry|@II45vH;37`alK49!ye&{5@Fy<QJe7eT)5*5z
z^RkM6%>-G^U>^X(d2chk&2D;UAcJxDW=wxDaKJmzJK_!vDsf`JNnjg~4Ogi0`OZbW
zINWWpE0;w1fY>6BO^hkGMEV=reC65M+@)lR{IWof@I>?nM<x`N$Qd5@DH!RecJXi&
z@&6TZcZ#?#<rQHO=O_UYl?Yfl{?=6cgLK^Isa0%j!M_dh#&z<)YvG+Bz%b5_)R>23
fAbN*9!l!_!6L;F-krHp?=%`*DE_Gwp=!gFSLDYhq

delta 1536
zcmY+Edu&rx9LLY^-nQ$ycI(=$TQ}OZ8+&xD8&KG~F$Np$mN^)SBH(3V8NFq6^u=v?
zcY`P(5~9Z69~eRc2?U9f89hW1Uo6omf-ps8EP)saJ_uk*7(x9*&nXh|r1$gvJ<spt
z+_vxi1m|vm;SGa9N7!<&cpz_h$KZufRis*~1|ky~!ZlJ2Q)Ac_sg-Jh2qaiDG=rD(
zCFdUpLf&G}qb1d`T2r_<VwJ3s5~(CoDwRguk~=a@nwHtm%yRWoeP*BRp#~fU8_dKD
z;DTBB0Q}&_R-wW$Tej^Yl1H{P&cU$YH_w%w%x;v+8Jpw^MlbzLSOPh^j)6ol8H_Go
zyo6d+S4Hi3B_Rh$5^(&vVl-);x{(k`IgY{0@C?49Euzb`n*m1Xh3t<7^+<}O0F8PJ
z9@F21hjgFeZTK%pm*vd`*h2RiFAJ<=wV5?OO@AmjAi^FREiMH3i|(?z0M^pclENo<
zyFP6@jG$!ehac$~TRWSFtIY`-E9(VVO+RrA101HU<@o>>+FMa1h^lBdT~~Prz(ki<
zmjdiUrDlK~_&dgO+UODij$%vg5K2Y*lGLJ<^W=u(BD;9@JX*uPl<$Ze!C=Ol)mH6E
z<#-lLXW{kQ-P*)@ffpt48(on~xhf}d+-NawBFcGr<FH>=%Oorfcj8XF6*l3ku7#SE
zU*0Tl!MLSR>^!oHZ<<F^{#3QRIYs2Hhs2ZHu(Pf?D^qnyz?lUFc(AS#w&U5l7a)Z`
zcRLK@9=8*A&=YQ1mpz%a=Fv;Se6P#w5|tO(aTE_nfWei8EuIQ&@t%PkI_2G_f-a2D
zzXf07sy3(QYhHE<pKtT%E;Dmd2*i{t_-R`qOyc)#9`DaQe}ZSS2ZPa|GLVcZ$}il{
z{da1AARG!tlgcQsyv2~{V!&Ao{Fq!|DSW+%key^|IS{?+CGURkPG4H+pobT96)x2f
zd(Abg^TfQfU1?FU=iVa>_c`|VrdhJ?immZmTjPYKbi(SKD05%4&zNvDFk_;mBArL<
zP4|eFH!$q&oib7Tvwy&j9u+y(ZEt7tmFP2Yy_jF!+e|KcA>%abmbQwQ#5qfw#7j+T
zZnswP#CSz#E7vQIPAAvvf}e1`A$AmSy;<CC;d-~h-@x^LS%;SEgPN!ExsEMtS;UMP
z%<}0w=4L`&f-f_4tVgA5@2M2WdU8$eJr1T0HS=+7#gsq*Pp|Z-RqRJTo2FMj6rdY_
zTQyU2j$h{&Sk|`<w0N-3r!HU>&Gbg!L5<;Eo@-%nnUwc&U!c7E1LjO-`y*?DvK)#I
zDj)KSQ#@E4iwC3q1EK!l<79s%CI`a_h4Pv^93OF<<ru@MK)vyIZr<gn;z*-Mp02jC
z`MtDHULmUO%zTZW9$W)(3QI#>aEJy%JHVD1m=lOa*M<iB;{(ZcN*?cba@@hchnm#v
zZ;u?sdF%U%nw8IacrC-EnAn<7Zgcln99=)hQO>HAGVY(}DCae*KrFshQFH$k3SlL8
zQXdXS67`S2`^m8E<(H`Nds6se6@E-*5AWb(l_<CBIqDex)V8vF*ccABDUH+^xednY
t<K%yzqxu-Y5E|n1tA=twmnKheF%XS8y#$^Jks*x7Et*V3!u|0#{{aq!wP^qV

diff --git a/litellm/integrations/__pycache__/supabase.cpython-311.pyc b/litellm/integrations/__pycache__/supabase.cpython-311.pyc
index ffb30cda5647964d1806b91391ffac8119d08529..ffc824e92a5470d62d7ef504fef77a0b56c2d3d9 100644
GIT binary patch
delta 20
acmaE1^1_6BIWI340}!mt`nHifRtf+`#s*6O

delta 20
acmaE1^1_6BIWI340}xC$e!7u6Rtf+^jRoxh

diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index e5b9c3993ef..d37cc1c4ef8 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -1,7 +1,7 @@
 #### What this tests ####
 #    This tests streaming for the completion endpoint
 
-import sys, os
+import sys, os, asyncio
 import traceback
 import time
 
@@ -102,6 +102,27 @@ def test_openai_chat_completion_call():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
+async def completion_call():
+    try:
+        response = completion(
+            model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
+        )
+        print(f"response: {response}")
+        complete_response = ""
+        start_time = time.time()
+        # Change for loop to async for loop
+        async for chunk in response:
+            chunk_time = time.time()
+            print(f"time since initial request: {chunk_time - start_time:.5f}")
+            print(chunk["choices"][0]["delta"])
+            complete_response += chunk["choices"][0]["delta"]["content"]
+        if complete_response == "": 
+            raise Exception("Empty response received")
+    except:
+        print(f"error occurred: {traceback.format_exc()}")
+        pass
+
+asyncio.run(completion_call())
 
 # # test on azure completion call
 # try:
@@ -191,7 +212,7 @@ def test_together_ai_completion_call_starcoder():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-# test on aleph alpha completion call
+# test on aleph alpha completion call - commented out as it's expensive to run this on circle ci for every build
 # def test_aleph_alpha_call():
 #     try:
 #         start_time = time.time()