Added kwargs to call_single (#46)

* added kwargs to call_single to allow customization when calling it directly * Added a test to check if kwargs is passed correctly * Updated tests * grouped kwargs tests in a subtest
Future-House · Jan 28, 2025 · 7d5c739 · 7d5c739
1 parent b6ca776
commit 7d5c739
Show file tree

Hide file tree

Showing 9 changed files with 1,336 additions and 1,136 deletions.
diff --git a/llmclient/llms.py b/llmclient/llms.py
@@ -359,9 +359,10 @@ async def call_single(
         output_type: type[BaseModel] | TypeAdapter | JSONSchema | None = None,
         tools: list[Tool] | None = None,
         tool_choice: Tool | str | None = TOOL_CHOICE_REQUIRED,
+        **kwargs,
     ) -> LLMResult:
         results = await self.call(
-            messages, callbacks, name, output_type, tools, tool_choice, n=1
+            messages, callbacks, name, output_type, tools, tool_choice, n=1, **kwargs
         )
         if not results:
             raise ValueError("No results returned from call")

diff --git a/tests/cassettes/TestLiteLLMModel.test_call_single[with-router].yaml b/tests/cassettes/TestLiteLLMModel.test_call_single[with-router].yaml
diff --git a/tests/cassettes/TestLiteLLMModel.test_call_single[without-router].yaml b/tests/cassettes/TestLiteLLMModel.test_call_single[without-router].yaml
diff --git a/tests/cassettes/TestLiteLLMModel.test_cost_call[Anthropic-model].yaml b/tests/cassettes/TestLiteLLMModel.test_cost_call[Anthropic-model].yaml
@@ -0,0 +1,85 @@
+interactions:
+  - request:
+      body:
+        '{"model": "claude-3-5-haiku-20241022", "messages": [{"role": "user", "content":
+        [{"type": "text", "text": "What is the meaning of the universe?"}]}], "temperature":
+        0, "max_tokens": 56, "system": [{"type": "text", "text": "Respond with single
+        words."}]}'
+      headers:
+        accept:
+          - application/json
+        accept-encoding:
+          - gzip, deflate
+        anthropic-version:
+          - "2023-06-01"
+        connection:
+          - keep-alive
+        content-length:
+          - "253"
+        content-type:
+          - application/json
+        host:
+          - api.anthropic.com
+        user-agent:
+          - litellm/1.59.5
+      method: POST
+      uri: https://api.anthropic.com/v1/messages
+    response:
+      body:
+        string: !!binary |
+          H4sIAAAAAAAAA2SOMWvDMBSE/8vNcrDVplCNXbpkrOkQilDkRyLbeXKkJ9Ji/N+LQwMtnQ7uuztu
+          RuhgcM5HWzdtv7vu0uHSvz21L8+U3g/9KzdQkK+J1hTl7I4EhRTH1XA5hyyOBQrn2NEIAz+60lH1
+          UG2rkwtDqXStH5taayj4yEIsMPv5vin0ubZvYtDywPHKGywfClniZBO5HBkGxJ2Vkhg/INOlEHuC
+          4TKOCuV2zcwIPBWxEgfiDKMbBe/8iaxP5CREtn8D9Z0nct1/Fov8drbL8g0AAP//AwD1M9oFMwEA
+          AA==
+      headers:
+        CF-RAY:
+          - 909370809f0f15e3-SJC
+        Connection:
+          - keep-alive
+        Content-Encoding:
+          - gzip
+        Content-Type:
+          - application/json
+        Date:
+          - Tue, 28 Jan 2025 19:37:51 GMT
+        Server:
+          - cloudflare
+        Transfer-Encoding:
+          - chunked
+        X-Robots-Tag:
+          - none
+        anthropic-ratelimit-input-tokens-limit:
+          - "5000000"
+        anthropic-ratelimit-input-tokens-remaining:
+          - "5000000"
+        anthropic-ratelimit-input-tokens-reset:
+          - "2025-01-28T19:37:51Z"
+        anthropic-ratelimit-output-tokens-limit:
+          - "1000000"
+        anthropic-ratelimit-output-tokens-remaining:
+          - "1000000"
+        anthropic-ratelimit-output-tokens-reset:
+          - "2025-01-28T19:37:51Z"
+        anthropic-ratelimit-requests-limit:
+          - "5000"
+        anthropic-ratelimit-requests-remaining:
+          - "4999"
+        anthropic-ratelimit-requests-reset:
+          - "2025-01-28T19:37:51Z"
+        anthropic-ratelimit-tokens-limit:
+          - "6000000"
+        anthropic-ratelimit-tokens-remaining:
+          - "6000000"
+        anthropic-ratelimit-tokens-reset:
+          - "2025-01-28T19:37:51Z"
+        cf-cache-status:
+          - DYNAMIC
+        request-id:
+          - req_01Eppf1xbA8q5A3TkRYsr68g
+        via:
+          - 1.1 google
+      status:
+        code: 200
+        message: OK
+version: 1
diff --git a/tests/cassettes/TestLiteLLMModel.test_cost_call[OpenAI-model].yaml b/tests/cassettes/TestLiteLLMModel.test_cost_call[OpenAI-model].yaml
@@ -0,0 +1,107 @@
+interactions:
+  - request:
+      body:
+        '{"messages": [{"role": "system", "content": "Respond with single words."},
+        {"role": "user", "content": "What is the meaning of the universe?"}], "model":
+        "gpt-4o-mini-2024-07-18", "max_tokens": 56, "temperature": 0}'
+      headers:
+        accept:
+          - application/json
+        accept-encoding:
+          - gzip, deflate
+        connection:
+          - keep-alive
+        content-length:
+          - "215"
+        content-type:
+          - application/json
+        host:
+          - api.openai.com
+        user-agent:
+          - AsyncOpenAI/Python 1.60.0
+        x-stainless-arch:
+          - arm64
+        x-stainless-async:
+          - async:asyncio
+        x-stainless-lang:
+          - python
+        x-stainless-os:
+          - MacOS
+        x-stainless-package-version:
+          - 1.60.0
+        x-stainless-raw-response:
+          - "true"
+        x-stainless-retry-count:
+          - "0"
+        x-stainless-runtime:
+          - CPython
+        x-stainless-runtime-version:
+          - 3.11.10
+      method: POST
+      uri: https://api.openai.com/v1/chat/completions
+    response:
+      body:
+        string: !!binary |
+          H4sIAAAAAAAAAwAAAP//jJJBT+MwEIXv+RXWnBuUlqKU3jhwQHBgkRAHhCLXniSmjseyJ7usUP87
+          clKaIFhpLznMN+/lzXjeMyHAaNgKUK1k1XmbX/W23fx6etjvLx4e63b55zEEurm7vLnt6B4WSUG7
+          V1T8qTpT1HmLbMiNWAWUjMl1WZ5visvzoiwG0JFGm2SN53xNeWecyVfFap0XZb7cHNUtGYURtuI5
+          E0KI9+GbcjqNb7AVg9dQ6TBG2SBsT01CQCCbKiBjNJGlY1hMUJFjdEP06zcTGZ3Cs3lDwLqPMoV0
+          vbXH+uH0R0uND7SLR36q18aZ2FYBZSSX3COTh4EeMiFehsn6L2HBB+o8V0x7dMlwtR7tYNrnBD8Z
+          E0s702wWP5hVGlkaG2eLASVVi3pSTluUvTY0A9ls5O9ZfvIexzau+R/7CSiFnlFXPqA26uu8U1vA
+          dGz/ajuteAgMEcNvo7BigyE9g8Za9nY8AYh/I2NX1cY1GHww4x3UvipXqEu5u1gryA7ZBwAAAP//
+          AwC1HS6hFQMAAA==
+      headers:
+        CF-Cache-Status:
+          - DYNAMIC
+        CF-RAY:
+          - 9093707c3c60174a-SJC
+        Connection:
+          - keep-alive
+        Content-Encoding:
+          - gzip
+        Content-Type:
+          - application/json
+        Date:
+          - Tue, 28 Jan 2025 19:37:51 GMT
+        Server:
+          - cloudflare
+        Set-Cookie:
+          - __cf_bm=dqIilPhCKBMWrfzBIKv4Z773uZfIHyMVkz9CwPgIUtA-1738093071-1.0.1.1-eLZ4cnMA8fb5u55VPgPzLBwaJH8MbcL3FaS_WIZ7m1Y2PPk00cpUZHpTcwEErfVXeYRqTRcDOGjb4niE.byJ3A;
+            path=/; expires=Tue, 28-Jan-25 20:07:51 GMT; domain=.api.openai.com; HttpOnly;
+            Secure; SameSite=None
+          - _cfuvid=VubHV4jc3NAG1.KYK.9ezrasy_FR9RQDSt8gSdEubnM-1738093071389-0.0.1.1-604800000;
+            path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+        Transfer-Encoding:
+          - chunked
+        X-Content-Type-Options:
+          - nosniff
+        access-control-expose-headers:
+          - X-Request-ID
+        alt-svc:
+          - h3=":443"; ma=86400
+        openai-organization:
+          - future-house-xr4tdh
+        openai-processing-ms:
+          - "490"
+        openai-version:
+          - "2020-10-01"
+        strict-transport-security:
+          - max-age=31536000; includeSubDomains; preload
+        x-ratelimit-limit-requests:
+          - "30000"
+        x-ratelimit-limit-tokens:
+          - "150000000"
+        x-ratelimit-remaining-requests:
+          - "29999"
+        x-ratelimit-remaining-tokens:
+          - "149999926"
+        x-ratelimit-reset-requests:
+          - 2ms
+        x-ratelimit-reset-tokens:
+          - 0s
+        x-request-id:
+          - req_e0ce487241223e824cc737d821b5495c
+      status:
+        code: 200
+        message: OK
+version: 1