release: 0.2.0

.devcontainer/Dockerfile

@@ -3,7 +3,7 @@ FROM mcr.microsoft.com/vscode/devcontainers/python:0-${VARIANT}
 
 USER vscode
 
-RUN curl -sSf https://rye-up.com/get | RYE_VERSION="0.15.2" RYE_INSTALL_OPTION="--yes" bash
+RUN curl -sSf https://rye-up.com/get | RYE_VERSION="0.24.0" RYE_INSTALL_OPTION="--yes" bash
 ENV PATH=/home/vscode/.rye/shims:$PATH
 
 RUN echo "[[ -d .venv ]] && source .venv/bin/activate" >> /home/vscode/.bashrc

.github/workflows/ci.yml

@@ -2,10 +2,10 @@ name: CI
 on:
   push:
     branches:
-      - main
+      - stainless
   pull_request:
     branches:
-      - main
+      - stainless
 
 jobs:
   lint:
@@ -21,7 +21,7 @@ jobs:
           curl -sSf https://rye-up.com/get | bash
           echo "$HOME/.rye/shims" >> $GITHUB_PATH
         env:
-          RYE_VERSION: 0.15.2
+          RYE_VERSION: 0.24.0
           RYE_INSTALL_OPTION: "--yes"
 
       - name: Install dependencies

.github/workflows/publish-pypi.yml

@@ -21,7 +21,7 @@ jobs:
           curl -sSf https://rye-up.com/get | bash
           echo "$HOME/.rye/shims" >> $GITHUB_PATH
         env:
-          RYE_VERSION: 0.15.2
+          RYE_VERSION: 0.24.0
           RYE_INSTALL_OPTION: "--yes"
 
       - name: Publish to PyPI

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.1.0"
+  ".": "0.2.0"
 }

CHANGELOG.md

@@ -1,5 +1,24 @@
 # Changelog
 
+## 0.2.0 (2024-02-21)
+
+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 ([#10](https://github.com/groq/groq-python/issues/10)) ([0c0d204](https://github.com/groq/groq-python/commit/0c0d20405a96167f060a03a2b8a58a49d9a1c7c8))
+* 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)) ([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))
+* update branch ([#8](https://github.com/groq/groq-python/issues/8)) ([b9b55b4](https://github.com/groq/groq-python/commit/b9b55b41cb158efd155f9cda829808c877493afd))
+
 ## 0.1.0 (2024-02-10)
 
 Full Changelog: [v0.0.1...v0.1.0](https://github.com/definitive-io/groqcloud-python/compare/v0.0.1...v0.1.0)

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

@@ -0,0 +1,45 @@
+from groq import Groq
+
+client = Groq()
+
+chat_completion = client.chat.completions.create(
+    #
+    # Required parameters
+    #
+    messages=[
+        # 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."},
+        # 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,
+)
+
+# Print the completion returned by the LLM.
+print(chat_completion.choices[0].message.content)

examples/chat_completion_async.py

@@ -0,0 +1,52 @@
+import asyncio
+
+from groq import AsyncGroq
+
+
+async def main():
+    client = AsyncGroq()
+
+    chat_completion = await client.chat.completions.create(
+        #
+        # Required parameters
+        #
+        messages=[
+            # 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."},
+            # 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,
+    )
+
+    # Print the completion returned by the LLM.
+    print(chat_completion.choices[0].message.content)
+
+
+asyncio.run(main())

examples/chat_completion_async_streaming.py

@@ -0,0 +1,51 @@
+import asyncio
+
+from groq import AsyncGroq
+
+
+async def main():
+    client = AsyncGroq()
+
+    stream = await client.chat.completions.create(
+        #
+        # Required parameters
+        #
+        messages=[
+            # 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."},
+            # 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,
+    )
+
+    # Print the incremental deltas returned by the LLM.
+    async for chunk in stream:
+        print(chunk.choices[0].delta.content, end="")
+
+
+asyncio.run(main())

examples/chat_completion_stop.py

@@ -0,0 +1,48 @@
+from groq import Groq
+
+client = Groq()
+
+chat_completion = client.chat.completions.create(
+    #
+    # Required parameters
+    #
+    messages=[
+        # 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."},
+        # 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, ...',
+        },
+    ],
+    # 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]".
+    # For this example, we will use ", 6" so that the llm stops counting at 5.
+    # 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,
+)
+
+# Print the completion returned by the LLM.
+print(chat_completion.choices[0].message.content)

examples/chat_completion_streaming.py

@@ -0,0 +1,46 @@
+from groq import Groq
+
+client = Groq()
+
+stream = client.chat.completions.create(
+    #
+    # Required parameters
+    #
+    messages=[
+        # 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."},
+        # 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,
+)
+
+# Print the incremental deltas returned by the LLM.
+for chunk in stream:
+    print(chunk.choices[0].delta.content, end="")

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "groq"
-version = "0.1.0"
+version = "0.2.0"
 description = "The official Python library for the groq API"
 readme = "README.md"
 license = "Apache-2.0"