Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update openai_pgvector_helloworld according to openai's migration guide #12

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update openai_pgvector_helloworld according to openai's migration guide #12

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 23 additions & 8 deletions openai_pgvector_helloworld/openai_pgvector_helloworld.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,8 +136,14 @@
"# Helper function: calculate cost of embedding num_tokens\n",
"# Assumes we're using the text-embedding-ada-002 model\n",
"# See https://openai.com/pricing\n",
"costs = {\n",
" \"text-embedding-3-small\": 0.020/1_000_000,\n",
" \"text-embedding-3-large\": 0.130/1_000_000,\n",
" \"text-embedding-ada-002\": 0.100/1_000_000,\n",
"}\n",
" \n",
"def get_embedding_cost(num_tokens):\n",
" return num_tokens/1000*0.0001\n",
" return num_tokens * costs['text-embedding-ada-002']\n",
"\n",
"# Helper function: calculate total cost of embedding all content in the dataframe\n",
"def get_total_embeddings_cost():\n",
Expand All @@ -151,11 +157,11 @@
"\n",
"# Helper function: get embeddings for a text\n",
"def get_embeddings(text):\n",
" response = openai.Embedding.create(\n",
" response = openai.embeddings.create(\n",
" model=\"text-embedding-ada-002\",\n",
" input = text.replace(\"\\n\",\" \")\n",
" )\n",
" embedding = response['data'][0]['embedding']\n",
" embedding = response.data[0].embedding\n",
" return embedding"
]
},
Expand Down Expand Up @@ -265,7 +271,7 @@
"# Save the dataframe with embeddings as a CSV file\n",
"df_new.to_csv('blog_data_and_embeddings.csv', index=False)\n",
"# It may also be useful to save as a json file, but we won't use this in the tutorial\n",
"#df_new.to_json('blog_data_and_embeddings.json')"
"df_new.to_json('blog_data_and_embeddings.json')"
]
},
{
Expand Down Expand Up @@ -506,14 +512,14 @@
"# Helper function: get text completion from OpenAI API\n",
"# Note max tokens is 4097\n",
"# Note we're using the latest gpt-3.5-turbo-0613 model\n",
"def get_completion_from_messages(messages, model=\"gpt-3.5-turbo-0613\", temperature=0, max_tokens=1000):\n",
" response = openai.ChatCompletion.create(\n",
"def get_completion_from_messages(messages, model=\"gpt-4o-mini-2024-07-18\", temperature=0, max_tokens=1000):\n",
" response = openai.chat.completions.create(\n",
" model=model,\n",
" messages=messages,\n",
" temperature=temperature, \n",
" max_tokens=max_tokens, \n",
" )\n",
" return response.choices[0].message[\"content\"]"
" return response.choices[0].message.content"
]
},
{
Expand Down Expand Up @@ -611,6 +617,15 @@
"print(input_2)\n",
"print(response_2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# References\n",
"- https://docs.timescale.com/self-hosted/latest/install/installation-docker/#install-self-hosted-timescaledb-from-a-pre-built-container\n",
"- https://github.com/openai/openai-python/discussions/742 (OpenAI migration guide)"
]
}
],
"metadata": {
Expand All @@ -629,7 +644,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.16"
"version": "3.11.6"
}
},
"nbformat": 4,
Expand Down