feat(assistants/main.py): add 'add_message' endpoint

litellm/assistants/main.py

@@ -24,7 +24,7 @@ def create_thread(
     metadata: Optional[dict] = None,
     tool_resources: Optional[OpenAICreateThreadParamsToolResources] = None,
     client: Optional[OpenAI] = None,
-    **kwargs
+    **kwargs,
 ) -> Thread:
     """
     - get the llm provider
@@ -115,4 +115,85 @@ def create_thread(
 
 ### MESSAGES ###
 
+
+def add_message(
+    custom_llm_provider: Literal["openai"],
+    thread_id: str,
+    role: Literal["user", "assistant"],
+    content: str,
+    attachments: Optional[List[Attachment]] = None,
+    metadata: Optional[dict] = None,
+    client: Optional[OpenAI] = None,
+    **kwargs,
+) -> OpenAIMessage:
+    ### COMMON OBJECTS ###
+    message_data = MessageData(
+        role=role, content=content, attachments=attachments, metadata=metadata
+    )
+    optional_params = GenericLiteLLMParams(**kwargs)
+
+    ### TIMEOUT LOGIC ###
+    timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
+    # set timeout for 10 minutes by default
+
+    if (
+        timeout is not None
+        and isinstance(timeout, httpx.Timeout)
+        and supports_httpx_timeout(custom_llm_provider) == False
+    ):
+        read_timeout = timeout.read or 600
+        timeout = read_timeout  # default 10 min timeout
+    elif timeout is not None and not isinstance(timeout, httpx.Timeout):
+        timeout = float(timeout)  # type: ignore
+    elif timeout is None:
+        timeout = 600.0
+
+    response: Optional[OpenAIMessage] = None
+    if custom_llm_provider == "openai":
+        api_base = (
+            optional_params.api_base  # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
+            or litellm.api_base
+            or os.getenv("OPENAI_API_BASE")
+            or "https://api.openai.com/v1"
+        )
+        organization = (
+            optional_params.organization
+            or litellm.organization
+            or os.getenv("OPENAI_ORGANIZATION", None)
+            or None  # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
+        )
+        # set API KEY
+        api_key = (
+            optional_params.api_key
+            or litellm.api_key  # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there
+            or litellm.openai_key
+            or os.getenv("OPENAI_API_KEY")
+        )
+        response = openai_assistants_api.add_message(
+            thread_id=thread_id,
+            message_data=message_data,
+            api_base=api_base,
+            api_key=api_key,
+            timeout=timeout,
+            max_retries=optional_params.max_retries,
+            organization=organization,
+            client=client,
+        )
+    else:
+        raise litellm.exceptions.BadRequestError(
+            message="LiteLLM doesn't support {} for 'create_thread'. Only 'openai' is supported.".format(
+                custom_llm_provider
+            ),
+            model="n/a",
+            llm_provider=custom_llm_provider,
+            response=httpx.Response(
+                status_code=400,
+                content="Unsupported provider",
+                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+            ),
+        )
+
+    return response
+
+
 ### RUNS ###

litellm/llms/openai.py

@@ -1268,6 +1268,8 @@ class OpenAIAssistantsAPI(BaseLLM):
             for k, v in received_args.items():
                 if k == "self" or k == "client":
                     pass
+                elif k == "api_base" and v is not None:
+                    data["base_url"] = v
                 elif v is not None:
                     data[k] = v
             openai_client = OpenAI(**data)  # type: ignore
@@ -1306,10 +1308,10 @@ class OpenAIAssistantsAPI(BaseLLM):
         self,
         thread_id: str,
         message_data: MessageData,
-        api_key: str,
+        api_key: Optional[str],
         api_base: Optional[str],
         timeout: Union[float, httpx.Timeout],
-        max_retries: int,
+        max_retries: Optional[int],
         organization: Optional[str],
         client: Optional[OpenAI] = None,
     ) -> OpenAIMessage:

litellm/tests/test_assistants.py

@@ -26,11 +26,11 @@ V0 Scope:
 """
 
 
-def test_create_thread_litellm():
+def test_create_thread_litellm() -> Thread:
     message: MessageData = {"role": "user", "content": "Hey, how's it going?"}  # type: ignore
     new_thread = create_thread(
         custom_llm_provider="openai",
-        messages=[message],
+        messages=[message],  # type: ignore
     )
 
     assert isinstance(
@@ -39,7 +39,19 @@ def test_create_thread_litellm():
     return new_thread
 
 
-test_create_thread_litellm()
+def test_add_message_litellm():
+    message: MessageData = {"role": "user", "content": "Hey, how's it going?"}  # type: ignore
+    new_thread = test_create_thread_litellm()
+
+    # add message to thread
+    message: MessageData = {"role": "user", "content": "Hey, how's it going?"}  # type: ignore
+    added_message = litellm.add_message(
+        thread_id=new_thread.id, custom_llm_provider="openai", **message
+    )
+
+    print(f"added message: {added_message}")
+
+    assert isinstance(added_message, Message)
 
 
 def test_create_thread_openai_direct() -> Thread:
@@ -68,7 +80,7 @@ def test_create_thread_openai_direct() -> Thread:
 def test_add_message_openai_direct():
     openai_api = OpenAIAssistantsAPI()
     # create thread
-    new_thread = test_create_thread()
+    new_thread = test_create_thread_openai_direct()
     # add message to thread
     message: MessageData = {"role": "user", "content": "Hey, how's it going?"}  # type: ignore
     added_message = openai_api.add_message(