Update openai to v1

README.md

@@ -13,7 +13,7 @@
 
 **🟢 Gorilla is Apache 2.0** With Gorilla being fine-tuned on MPT, and Falcon, you can use Gorilla commercially with no obligations! :golf:  
 
-**:rocket: Try Gorilla in 60s** [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1DEBPsccVLF_aUnmD0FwPeHFrtdC0QIUP?usp=sharing) 
+**:rocket: Try Gorilla in 60s** [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1q7T7g3wmRNEUwsWujLcgjHLK7YNPjQxh?usp=sharing) 
 
 :computer: Use [Gorilla in your CLI](https://github.com/gorilla-llm/gorilla-cli) with `pip install gorilla-cli`
 
@@ -36,12 +36,12 @@
 - 🟢 [06/06] Released Commercially usable, Apache 2.0 licensed Gorilla models
 - :rocket: [05/30] Provided the [CLI interface](inference/README.md) to chat with Gorilla!
 - :rocket: [05/28] Released Torch Hub and TensorFlow Hub Models!
-- :rocket: [05/27] Released the first Gorilla model! [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1DEBPsccVLF_aUnmD0FwPeHFrtdC0QIUP?usp=sharing) or [:hugs:](https://huggingface.co/gorilla-llm/gorilla-7b-hf-delta-v0)!
+- :rocket: [05/27] Released the first Gorilla model! [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1q7T7g3wmRNEUwsWujLcgjHLK7YNPjQxh?usp=sharing) or [:hugs:](https://huggingface.co/gorilla-llm/gorilla-7b-hf-delta-v0)!
 - :fire: [05/27] We released the APIZoo contribution guide for community API contributions!
 - :fire: [05/25] We release the APIBench dataset and the evaluation code of Gorilla!
 
 ## Gorilla Gradio
-**Try Gorilla LLM models in [HF Spaces](https://huggingface.co/spaces/gorilla-llm/gorilla-demo/) or [![Gradio Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ktnVWPJOgqTC9hLW8lJPVZszuIddMy7y?usp=sharing)**
+**Try Gorilla LLM models in [HF Spaces](https://huggingface.co/spaces/gorilla-llm/gorilla-demo/) or [![Gradio Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/18ru6QUVVegJGTTa9TzbLAXVok42KDkWx?usp=sharing)**
 ![gorilla_webUI_2](https://github.com/TanmayDoesAI/gorilla/assets/85993243/f30645bf-6798-4bd2-ac6e-6943840ae095)
 
 

eval/get_llm_responses.py

@@ -58,14 +58,16 @@ def get_response(get_response_input, api_key):
 
     try:
         if "gpt" in model:
-            openai.api_key = api_key
-            responses = openai.ChatCompletion.create(
+            client = openai.OpenAI(
+                api_key=api_key,
+            )
+            responses = client.chat.completions.create(
                 model=model,
                 messages=question,
-                n=1,
+                n = 1,
                 temperature=0,
             )
-            response = responses['choices'][0]['message']['content']
+            response = responses.choices[0].message.content
         elif "claude" in model:
             client = anthropic.Anthropic(api_key=api_key)
             responses = client.completions.create(

eval/get_llm_responses_retriever.py

@@ -59,14 +59,16 @@ def get_response(get_response_input, api_key):
 
     try:
         if "gpt" in model:
-            openai.api_key = api_key
-            responses = openai.ChatCompletion.create(
+            client = openai.OpenAI(
+                api_key=api_key,
+            )
+            responses = client.chat.completions.create(
                 model=model,
                 messages=question,
-                n=1,
+                n = 1,
                 temperature=0,
             )
-            response = responses['choices'][0]['message']['content']
+            response = responses.choices[0].message.content
         elif "claude" in model:
             client = anthropic.Anthropic(api_key=api_key)
             responses = client.completions.create(

eval/retrievers/gpt.py

@@ -36,10 +36,10 @@ def get_embeddings(
     ) -> List[List[float]]:
         assert len(list_of_text) <= 2048, "The number of docs should be <= 2048"
         list_of_text = [text.replace("\n", " ") for text in list_of_text]
-        openai.api_key = os.environ["OPENAI_API_KEY"]
-        data = openai.Embedding.create(input=list_of_text, engine="text-embedding-ada-002").data
-        data = sorted(data, key=lambda x: x["index"])  # maintain the same order as input.
-        return [d["embedding"] for d in data]
+        client = openai.OpenAI()  # os.environ["OPENAI_API_KEY"] is default
+        data = client.embeddings.create(input=list_of_text,model="text-embedding-ada-002").data
+        data = sorted(data, key=lambda x: x.index)  # maintain the same order as input.
+        return [d.embedding for d in data]
 
     def from_documents(self, documents: List):
         contents = [document.page_content for document in documents]

inference/README.md

@@ -4,7 +4,7 @@
 
 ## Get Started
 
-You can either run Gorilla through our hosted [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1DEBPsccVLF_aUnmD0FwPeHFrtdC0QIUP?usp=sharing) or [chat with it using cli](#inference-using-cli). We also provide instructions for [evaluating batched prompts](#optional-batch-inference-on-a-prompt-file). Here, are the instructions to run it locally.
+You can either run Gorilla through our hosted [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1q7T7g3wmRNEUwsWujLcgjHLK7YNPjQxh?usp=sharing) or [chat with it using cli](#inference-using-cli). We also provide instructions for [evaluating batched prompts](#optional-batch-inference-on-a-prompt-file). Here, are the instructions to run it locally.
 
 New: We release `gorilla-mpt-7b-hf-v0` and `gorilla-falcon-7b-hf-v0` - two Apache 2.0 licensed models (commercially usable). 
 

openfunctions/README.md

@@ -35,7 +35,7 @@ All of our models are hosted on our Huggingface UC Berkeley gorilla-llm org: [go
 1. OpenFunctions is compatible with OpenAI Functions
 
 ```bash
-!pip install openai==0.28.1
+!pip install openai
 ```
 
 2. Point to Gorilla hosted servers
@@ -44,14 +44,16 @@ All of our models are hosted on our Huggingface UC Berkeley gorilla-llm org: [go
 import openai
 
 def get_gorilla_response(prompt="Call me an Uber ride type \"Plus\" in Berkeley at zipcode 94704 in 10 minutes", model="gorilla-openfunctions-v0", functions=[]):
-  openai.api_key = "EMPTY"
-  openai.api_base = "http://luigi.millennium.berkeley.edu:8000/v1"
   try:
-    completion = openai.ChatCompletion.create(
+    client = openai.OpenAI(
+      api_key = "EMPTY",
+      base_url = "http://luigi.millennium.berkeley.edu:8000/v1"
+    )
+    completion = client.chat.completions.create(
       model="gorilla-openfunctions-v2",
       temperature=0.0,
       messages=[{"role": "user", "content": prompt}],
-      functions=functions,
+      tools=functions,
     )
     return completion.choices[0]
   except Exception as e:
@@ -64,19 +66,22 @@ def get_gorilla_response(prompt="Call me an Uber ride type \"Plus\" in Berkeley
 query = "What's the weather like in the two cities of Boston and San Francisco?"
 functions = [
     {
-        "name": "get_current_weather",
-        "description": "Get the current weather in a given location",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
+        "type": "function",
+        "function": {
+            "name": "get_current_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    },
+                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                 },
-                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                "required": ["location"],
             },
-            "required": ["location"],
-        },
+        }
     }
 ]
 get_gorilla_response(query, functions=functions)

openfunctions/inference_hosted.py

@@ -1,9 +1,6 @@
 import openai
 import json
 
-openai.api_key = "EMPTY"
-openai.api_base = "http://luigi.millennium.berkeley.edu:8000/v1"
-
 # Example dummy function hard coded to return the same weather
 # In production, this could be your backend API or an external API
 def get_current_weather(location, unit="fahrenheit"):
@@ -21,26 +18,33 @@ def run_conversation():
     messages = [{"role": "user", "content": "What's the weather like in the two cities of Boston and San Francisco?"}]
     functions = [
         {
-            "name": "get_current_weather",
-            "description": "Get the current weather in a given location",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "location": {
-                        "type": "string",
-                        "description": "The city and state, e.g. San Francisco, CA",
+            "type": "function",
+            "function": {
+                "name": "get_current_weather",
+                "description": "Get the current weather in a given location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        },
+                        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                     },
-                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                    "required": ["location"],
                 },
-                "required": ["location"],
-            },
+            }
         }
     ]
-    completion = openai.ChatCompletion.create(
+    client = openai.OpenAI(
+        api_key = "EMPTY",
+        base_url = "http://luigi.millennium.berkeley.edu:8000/v1"
+    )
+    completion = client.chat.completions.create(
         model='gorilla-openfunctions-v2',
         messages=messages,
-        functions=functions,
-        function_call="auto",  # auto is default, but we'll be explicit
+        tools=functions,
+        tool_choice="auto",  # auto is default, but we'll be explicit
     )
 
     print("--------------------")

openfunctions/inference_local.py

@@ -79,26 +79,46 @@ def format_response(response: str):
 query_1: str = "What's the weather like in the two cities of Boston and San Francisco?"
 functions_1 = [
     {
-        "name": "get_current_weather",
-        "description": "Get the current weather in a given location",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
+        "type": "function",
+        "function": {
+            "name": "get_current_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    },
+                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                 },
-                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                "required": ["location"],
             },
-            "required": ["location"],
-        },
+        }
     }
 ]
 
 # Example usage 2
 #  This should return an error since the function cann't help with the prompt
 query_2: str = "What is the freezing point of water at a pressure of 10 kPa?"
-functions_2 = [{"name": "thermodynamics.calculate_boiling_point", "description": "Calculate the boiling point of a given substance at a specific pressure.", "parameters": {"type": "object", "properties": {"substance": {"type": "string", "description": "The substance for which to calculate the boiling point."}, "pressure": {"type": "number", "description": "The pressure at which to calculate the boiling point."}, "unit": {"type": "string", "description": "The unit of the pressure. Default is 'kPa'."}}, "required": ["substance", "pressure"]}}]
+functions_2 = [
+    {
+        "type": "function",
+        "function": {
+            "name": "thermodynamics.calculate_boiling_point", 
+            "description": "Calculate the boiling point of a given substance at a specific pressure.", 
+            "parameters": {
+                "type": "object", 
+                "properties": {
+                    "substance": {"type": "string", "description": "The substance for which to calculate the boiling point."},
+                    "pressure": {"type": "number", "description": "The pressure at which to calculate the boiling point."},
+                    "unit": {"type": "string", "description": "The unit of the pressure. Default is 'kPa'."}
+                }, 
+                "required": ["substance", "pressure"]
+            }
+        }
+    }
+]
 
 # Generate prompt and obtain model output
 prompt_1 = get_prompt(query_1, functions=functions_1)