implementing initial LLM class

2026-01-10 00:28:31 +00:00 · 2024-09-22 22:37:29 -03:00
parent 000e2666fb
commit 18c3925fa3
15 changed files with 2217 additions and 47 deletions
--- a/tests/cassettes/test_llm_call_with_all_attributes.yaml
+++ b/tests/cassettes/test_llm_call_with_all_attributes.yaml
@@ -0,0 +1,101 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Say ''Hello, World!'' and then
+      say STOP"}], "model": "gpt-3.5-turbo", "frequency_penalty": 0.1, "max_tokens":
+      50, "presence_penalty": 0.1, "stop": ["STOP"], "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '217'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=FFmP82tY.BP0BFYwK4ix5zIa5fG5Ye7tnJ1DN70SSx4-1727048166266-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.47.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.47.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AARioD9fe66arqP951Q6m1N5BgDqV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1727053206,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Hello, World!\\n\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 17,\n    \"completion_tokens\":
+      4,\n    \"total_tokens\": 21,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+      0\n    }\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8c76988ceede8759-MIA
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 23 Sep 2024 01:00:06 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=XKEjZqa9jLHDkJm09f6GoOFObGBsS.2iO2iQsVxfDtg-1727053206-1.0.1.1-AhT2h4tFAfFhcbWhI7x8he9L6T0eCndS2.n6pMSK3iFkx0qYlA5Y.iniDaQVaO1ukiEEoEJGaV2tL967WYm1uA;
+        path=/; expires=Mon, 23-Sep-24 01:30:06 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=ntPBCCgVUz_nq5Umsn4Dh2nras_FFFm.Om6wrSeiU00-1727053206899-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '110'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15552000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '50000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '49999938'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e2bb166ffe6d65c17da2b1d3afaef830
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1