Merge branch 'main' into dev/openai_api_base

docs/my-website/docs/tutorials/text_completion.md

@@ -0,0 +1,39 @@
+# Using Text Completion Format - with Completion()
+
+If your prefer interfacing with the OpenAI Text Completion format this tutorial covers how to use LiteLLM in this format
+```python
+response = openai.Completion.create(
+    model="text-davinci-003",
+    prompt='Write a tagline for a traditional bavarian tavern',
+    temperature=0,
+    max_tokens=100)
+```
+
+## Using LiteLLM in the Text Completion format
+### With gpt-3.5-turbo
+```python
+from litellm import text_completion
+response = text_completion(
+    model="gpt-3.5-turbo",
+    prompt='Write a tagline for a traditional bavarian tavern',
+    temperature=0,
+    max_tokens=100)
+```
+
+### With text-davinci-003
+```python
+response = text_completion(
+    model="text-davinci-003",
+    prompt='Write a tagline for a traditional bavarian tavern',
+    temperature=0,
+    max_tokens=100)
+```
+
+### With llama2
+```python
+response = text_completion(
+    model="togethercomputer/llama-2-70b-chat",
+    prompt='Write a tagline for a traditional bavarian tavern',
+    temperature=0,
+    max_tokens=100)
+```

docs/my-website/sidebars.js

@@ -43,6 +43,7 @@ const sidebars = {
         'tutorials/TogetherAI_liteLLM', 
         'tutorials/fallbacks', 
         'tutorials/finetuned_chat_gpt',
+        'tutorials/text_completion',
         'tutorials/ab_test_llms',
         'tutorials/litellm_Test_Multiple_Providers'
       ],

litellm/main.py

@@ -1,7 +1,7 @@
 import os, openai, sys
 from typing import Any
 from functools import partial
-import dotenv, traceback, random, asyncio, time
+import dotenv, traceback, random, asyncio, time, contextvars
 from copy import deepcopy
 import litellm
 from litellm import (  # type: ignore
@@ -49,8 +49,12 @@ async def acompletion(*args, **kwargs):
     # Use a partial function to pass your keyword arguments
     func = partial(completion, *args, **kwargs)
 
+    # Add the context to the function
+    ctx = contextvars.copy_context()
+    func_with_context = partial(ctx.run, func)
+
     # Call the synchronous function using run_in_executor
-    return await loop.run_in_executor(None, func)
+    return await loop.run_in_executor(None, func_with_context)
 
 
 @client
@@ -60,8 +64,8 @@ async def acompletion(*args, **kwargs):
 )  ## set timeouts, in case calls hang (e.g. Azure) - default is 600s, override with `force_timeout`
 def completion(
     model,
-    messages,  # required params
     # Optional OpenAI params: see https://platform.openai.com/docs/api-reference/chat/create
+    messages=[],
     functions=[],
     function_call="",  # optional params
     temperature=1,
@@ -212,9 +216,9 @@ def completion(
             # note: if a user sets a custom base - we should ensure this works
             # allow for the setting of dynamic and stateful api-bases
             api_base = (
-                custom_api_base or litellm.api_base or get_secret("OPENAI_API_BASE")
+                custom_api_base or litellm.api_base or get_secret("OPENAI_API_BASE") or "https://api.openai.com/v1"
             )
-            openai.api_base = api_base or "https://api.openai.com/v1"
+            openai.api_base = api_base
             openai.api_version = None
             if litellm.organization:
                 openai.organization = litellm.organization
@@ -861,6 +865,13 @@ def embedding(
             custom_llm_provider="azure" if azure == True else None,
         )
 
+###### Text Completion ################
+def text_completion(*args, **kwargs):
+    if 'prompt' in kwargs:
+        messages = [{'role': 'system', 'content': kwargs['prompt']}]
+        kwargs['messages'] = messages
+        kwargs.pop('prompt')
+        return completion(*args, **kwargs)
 
 ####### HELPER FUNCTIONS ################
 ## Set verbose to true -> ```litellm.set_verbose = True```

litellm/tests/test_completion.py

@@ -10,7 +10,7 @@ sys.path.insert(
 )  # Adds the parent directory to the system path
 import pytest
 import litellm
-from litellm import embedding, completion
+from litellm import embedding, completion, text_completion
 
 # from infisical import InfisicalClient
 
@@ -142,6 +142,17 @@ def test_completion_openai():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
+def test_completion_openai_prompt():
+    try:
+        response = text_completion(model="gpt-3.5-turbo", prompt="What's the weather in SF?")
+        response_str = response["choices"][0]["message"]["content"]
+        response_str_2 = response.choices[0].message.content
+        print(response)
+        assert response_str == response_str_2
+        assert type(response_str) == str
+        assert len(response_str) > 1
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
 
 def test_completion_text_openai():
     try:

litellm/utils.py

@@ -1444,13 +1444,12 @@ def get_secret(secret_name):
     if litellm.secret_manager_client != None:
         # TODO: check which secret manager is being used
         # currently only supports Infisical
+        try:
             secret = litellm.secret_manager_client.get_secret(
                 secret_name).secret_value
-        if secret != None:
+        except:
-            return secret  # if secret found in secret manager return it
+            secret = None
-        else:
+        return secret
-            raise ValueError(
-                f"Secret '{secret_name}' not found in secret manager")
     elif litellm.api_key != None:  # if users use litellm default key
         return litellm.api_key
     else:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.492"
+version = "0.1.494"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"