release: 0.2.0

.github/workflows/ci.yml

@@ -2,10 +2,10 @@ name: CI
 on:
   push:
     branches:
-      - main
+      - stainless
   pull_request:
     branches:
-      - main
+      - stainless
 
 jobs:
   lint:

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.4.0"
+  ".": "0.2.0"
 }

CHANGELOG.md

@@ -1,19 +1,21 @@
 # Changelog
 
-## 0.4.0 (2024-02-14)
+## 0.2.0 (2024-02-16)
 
-Full Changelog: [v0.1.0...v0.4.0](https://github.com/groq/groq-python/compare/v0.1.0...v0.4.0)
+Full Changelog: [v0.1.0...v0.2.0](https://github.com/groq/groq-python/compare/v0.1.0...v0.2.0)
 
 ### Features
 
+* Add initial Stainless SDK ([d5a8512](https://github.com/groq/groq-python/commit/d5a851262e04e625dde130367ed91d8f95683599))
 * Add initial Stainless SDK ([316de2c](https://github.com/groq/groq-python/commit/316de2ccfeb76e36fe34bb8656ea90a8d42a7d00))
 * create default branch ([7e00266](https://github.com/groq/groq-python/commit/7e00266e3c691d92d508e753e2c14c03297c09f9))
-* update via SDK Studio ([#3](https://github.com/groq/groq-python/issues/3)) ([2241036](https://github.com/groq/groq-python/commit/2241036e9dbee6629ad7ebce5e6f4f5e5f1028ce))
+* update via SDK Studio ([#3](https://github.com/groq/groq-python/issues/3)) ([8d92c08](https://github.com/groq/groq-python/commit/8d92c086e320c2715e02bc79807ff872e84c0b0f))
 
 
 ### Chores
 
-* go live ([#2](https://github.com/groq/groq-python/issues/2)) ([13665ad](https://github.com/groq/groq-python/commit/13665ad76705513d99cbaa497ccccc694932f2c3))
+* go live ([#2](https://github.com/groq/groq-python/issues/2)) ([ba81c42](https://github.com/groq/groq-python/commit/ba81c42d6d0fd6d47819e0d58962235cb70ca4f1))
+* go live ([#5](https://github.com/groq/groq-python/issues/5)) ([af9a838](https://github.com/groq/groq-python/commit/af9a838e240bb0f7385bc33fb18ce246427ca2f7))
 
 ## 0.1.0 (2024-02-10)
 

README.md

@@ -261,9 +261,9 @@ completion = response.parse()  # get the object that `chat.completions.create()`
 print(completion.id)
 ```
 
-These methods return an [`APIResponse`](https://github.com/groq/groq-python/tree/main/src/groq/_response.py) object.
+These methods return an [`APIResponse`](https://github.com/groq/groq-python/tree/stainless/src/groq/_response.py) object.
 
-The async client returns an [`AsyncAPIResponse`](https://github.com/groq/groq-python/tree/main/src/groq/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
+The async client returns an [`AsyncAPIResponse`](https://github.com/groq/groq-python/tree/stainless/src/groq/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
 
 #### `.with_streaming_response`
 

bin/check-release-environment

@@ -6,9 +6,9 @@ if [ -z "${PYPI_TOKEN}" ]; then
   errors+=("The GROQ_PYPI_TOKEN secret has not been set. Please set it in either this repository's secrets or your organization secrets.")
 fi
 
-len=${#errors[@]}
+lenErrors=${#errors[@]}
 
-if [[ len -gt 0 ]]; then
+if [[ lenErrors -gt 0 ]]; then
   echo -e "Found the following errors in the release environment:\n"
 
   for error in "${errors[@]}"; do

examples/chat_completion.py

@@ -10,43 +10,33 @@
         # Set an optional system message. This sets the behavior of the
         # assistant and can be used to provide specific instructions for
         # how it should behave throughout the conversation.
-        {
-            "role": "system",
-            "content": "you are a helpful assistant."
-        },
+        {"role": "system", "content": "you are a helpful assistant."},
         # Set a user message for the assistant to respond to.
         {
             "role": "user",
             "content": "Explain the importance of low latency LLMs",
         },
     ],
-
     # The language model which will generate the completion.
     model="mixtral-8x7b-32768",
-
     #
     # Optional parameters
     #
-
     # Controls randomness: lowering results in less random completions.
     # As the temperature approaches zero, the model will become deterministic
     # and repetitive.
     temperature=0.5,
-
     # The maximum number of tokens to generate. Requests can use up to
     # 2048 tokens shared between prompt and completion.
     max_tokens=1024,
-
     # Controls diversity via nucleus sampling: 0.5 means half of all
     # likelihood-weighted options are considered.
     top_p=1,
-
     # A stop sequence is a predefined or user-specified text string that
     # signals an AI to stop generating content, ensuring its responses
     # remain focused and concise. Examples include punctuation marks and
     # markers like "[end]".
     stop=None,
-
     # If set, partial message deltas will be sent.
     stream=False,
 )

examples/chat_completion_async.py

@@ -14,43 +14,33 @@ async def main():
             # Set an optional system message. This sets the behavior of the
             # assistant and can be used to provide specific instructions for
             # how it should behave throughout the conversation.
-            {
-                "role": "system",
-                "content": "you are a helpful assistant."
-            },
+            {"role": "system", "content": "you are a helpful assistant."},
             # Set a user message for the assistant to respond to.
             {
                 "role": "user",
                 "content": "Explain the importance of low latency LLMs",
             },
         ],
-
         # The language model which will generate the completion.
         model="mixtral-8x7b-32768",
-
         #
         # Optional parameters
         #
-
         # Controls randomness: lowering results in less random completions.
         # As the temperature approaches zero, the model will become
         # deterministic and repetitive.
         temperature=0.5,
-
         # The maximum number of tokens to generate. Requests can use up to
         # 2048 tokens shared between prompt and completion.
         max_tokens=1024,
-
         # Controls diversity via nucleus sampling: 0.5 means half of all
         # likelihood-weighted options are considered.
         top_p=1,
-
         # A stop sequence is a predefined or user-specified text string that
         # signals an AI to stop generating content, ensuring its responses
         # remain focused and concise. Examples include punctuation marks and
         # markers like "[end]".
         stop=None,
-
         # If set, partial message deltas will be sent.
         stream=False,
     )

examples/chat_completion_async_streaming.py

@@ -14,39 +14,30 @@ async def main():
             # Set an optional system message. This sets the behavior of the
             # assistant and can be used to provide specific instructions for
             # how it should behave throughout the conversation.
-            {
-                "role": "system",
-                "content": "you are a helpful assistant."
-            },
+            {"role": "system", "content": "you are a helpful assistant."},
             # Set a user message for the assistant to respond to.
             {
                 "role": "user",
                 "content": "Explain the importance of low latency LLMs",
             },
         ],
-
         # The language model which will generate the completion.
         model="mixtral-8x7b-32768",
-
         #
         # Optional parameters
         #
-
         # Controls randomness: lowering results in less random completions.
         # As the temperature approaches zero, the model will become
         # deterministic and repetitive.
         temperature=0.5,
-
         # The maximum number of tokens to generate. Requests can use up to
         # 2048 tokens shared between prompt and completion.
         max_tokens=1024,
-
         # A stop sequence is a predefined or user-specified text string that
         # signals an AI to stop generating content, ensuring its responses
         # remain focused and concise. Examples include punctuation marks and
         # markers like "[end]".
         stop=None,
-
         # Controls diversity via nucleus sampling: 0.5 means half of all
         # likelihood-weighted options are considered.
         stream=True,

examples/chat_completion_stop.py

@@ -10,37 +10,28 @@
         # Set an optional system message. This sets the behavior of the
         # assistant and can be used to provide specific instructions for
         # how it should behave throughout the conversation.
-        {
-            "role": "system",
-            "content": "you are a helpful assistant."
-        },
+        {"role": "system", "content": "you are a helpful assistant."},
         # Set a user message for the assistant to respond to.
         {
             "role": "user",
-            "content": "Count to 10.  Your response must begin with \"1, \".  example: 1, 2, 3, ...",
+            "content": 'Count to 10.  Your response must begin with "1, ".  example: 1, 2, 3, ...',
         },
     ],
-
     # The language model which will generate the completion.
     model="mixtral-8x7b-32768",
-
     #
     # Optional parameters
     #
-
     # Controls randomness: lowering results in less random completions.
     # As the temperature approaches zero, the model will become deterministic
     # and repetitive.
     temperature=0.5,
-
     # The maximum number of tokens to generate. Requests can use up to
     # 2048 tokens shared between prompt and completion.
     max_tokens=1024,
-
     # Controls diversity via nucleus sampling: 0.5 means half of all
     # likelihood-weighted options are considered.
     top_p=1,
-
     # A stop sequence is a predefined or user-specified text string that
     # signals an AI to stop generating content, ensuring its responses
     # remain focused and concise. Examples include punctuation marks and
@@ -49,7 +40,6 @@
     # If multiple stop values are needed, an array of string may be passed,
     # stop=[", 6", ", six", ", Six"]
     stop=", 6",
-
     # If set, partial message deltas will be sent.
     stream=False,
 )

examples/chat_completion_streaming.py

@@ -10,43 +10,33 @@
         # Set an optional system message. This sets the behavior of the
         # assistant and can be used to provide specific instructions for
         # how it should behave throughout the conversation.
-        {
-            "role": "system",
-            "content": "you are a helpful assistant."
-        },
+        {"role": "system", "content": "you are a helpful assistant."},
         # Set a user message for the assistant to respond to.
         {
             "role": "user",
             "content": "Explain the importance of low latency LLMs",
         },
     ],
-
     # The language model which will generate the completion.
     model="mixtral-8x7b-32768",
-
     #
     # Optional parameters
     #
-
     # Controls randomness: lowering results in less random completions.
     # As the temperature approaches zero, the model will become deterministic
     # and repetitive.
     temperature=0.5,
-
     # The maximum number of tokens to generate. Requests can use up to
     # 2048 tokens shared between prompt and completion.
     max_tokens=1024,
-
     # Controls diversity via nucleus sampling: 0.5 means half of all
     # likelihood-weighted options are considered.
     top_p=1,
-
     # A stop sequence is a predefined or user-specified text string that
     # signals an AI to stop generating content, ensuring its responses
     # remain focused and concise. Examples include punctuation marks and
     # markers like "[end]".
     stop=None,
-
     # If set, partial message deltas will be sent.
     stream=True,
 )

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "groq"
-version = "0.4.0"
+version = "0.2.0"
 description = "The official Python library for the groq API"
 readme = "README.md"
 license = "Apache-2.0"

src/groq/_streaming.py

@@ -53,8 +53,6 @@ def __stream__(self) -> Iterator[_T]:
         iterator = self._iter_events()
 
         for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
             yield process_data(data=sse.json(), cast_to=cast_to, response=response)
 
         # Ensure the entire stream is consumed
@@ -108,8 +106,6 @@ async def __aiter__(self) -> AsyncIterator[_T]:
 
     async def _iter_events(self) -> AsyncIterator[ServerSentEvent]:
         async for sse in self._decoder.aiter(self.response.aiter_lines()):
-            if sse.data.startswith("[DONE]"):
-                break
             yield sse
 
     async def __stream__(self) -> AsyncIterator[_T]:

src/groq/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless.
 
 __title__ = "groq"
-__version__ = "0.4.0"  # x-release-please-version
+__version__ = "0.2.0"  # x-release-please-version