Rodolfo/openai-api
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: Rodolfo:70194de64ceaa2666ecc44be7aad5e896a644046
Branches Tags
Rodolfo:main
...
compare: Rodolfo:22dc9e7275484137daefbaa3f3f57c0c1fde10a0
Branches Tags
Rodolfo:main

10 commits
70194de64c ... 22dc9e7275

Author SHA1 Message Date
Rodolfo Barcelli Jo 22dc9e7275 Add: input image field for create_image.py 2025-09-17 20:47:14 +08:00
Enrique Barcelli 2032483e64
Update SECURIT.md 2025-09-06 00:31:59 +08:00
Enrique Barcelli 4789b9355d
Add extraction and display of the model response text from the json API response 2025-09-06 00:29:31 +08:00
Enrique Barcelli 78bb591bd3
Change data type of vector_store to list so that multiple vector stores could be included in the file_search 2025-09-05 23:08:50 +08:00
Enrique Barcelli d09a57062c
Add printing of the text part of the retrieved message for proper encoding 2025-09-02 08:42:16 +08:00
Enrique Barcelli c14e81fd86
Update documentation 2025-09-01 18:03:04 +08:00
Enrique Barcelli 8d8cd8950f
Add image generation functionality 2025-09-01 17:56:12 +08:00
Enrique Barcelli 98660d372b
Update SECURITY.md 2025-08-31 23:56:57 +08:00
Enrique Barcelli ed86a269c1
Update README.md 2025-08-31 23:55:41 +08:00
Enrique Barcelli 74e940c45d
Add funcionality to add metadata to vector stores and vectore store files 2025-08-31 23:47:56 +08:00
11 changed files with 143 additions and 31 deletions
Show stats Expand all files Collapse all files

1
.gitignore vendored
View file

@ -1,5 +1,6 @@
# Sensitive files
config.py
*.png
# ---> Python
# Byte-compiled / optimized / DLL files

61
README.md
View file

@ -23,34 +23,37 @@ You can manipulate the main abstractions of the OpenAI model:
* Each script has a number of mandatory parameters in strict order:
| Script | Parameter 1 | Parameter 2 | Parameter 3 | Purpose |
| --------------------------------------- | ----------------- | --------------- | --------------- | -------------------------------------------------------- |
| `cancel_model_response.py` | `response_id` | | | Cancel a Response running in the background |
| `create_conversation.py` | | | | Create a new Conversation |
| `create_model_response.py` | `conversation_id` | `model_id` | `input_message` | Create a Response within a Conversation |
| `create_text_item.py` | `conversation_id` | `input_message` | | Create a user input or instruction within a Conversation |
| `create_vector_store.py` | | | | Create a Vector Store |
| `create_vector_store_file.py` | `vector_store_id` | `file_id` | | Create a File in a Vector Store |
| `delete_conversation.py` | `conversation_id` | | | Delete a Conversation |
| `delete_file.py` | `file_id` | | | Delete a File |
| `delete_item.py` | `conversation_id` | `item_id` | | Delete an Item (input or Response) from a Conversation |
| `delete_model_response.py` | `response_id` | | | Delete a Response |
| `delete_vector_store.py` | `vector_store_id` | | | Delete a Vector Store |
| `delete_vector_store_file.py` | `vector_store_id` | `file_id` | | Delete a File from a Vector Store |
| `list_files.py` | | | | List all uploaded Files |
| `list_input_items.py` | `response_id` | | | List all input Items used to generate a Response |
| `list_items.py` | `conversation_id` | | | List all Items (inputs or Responses) in a Conversation |
| `list_vector_store_files.py` | `vector_store_id` | | | List all Files in a Vector Store |
| `list_vector_stores.py` | | | | List all Vector Stores |
| `retrieve_conversation.py` | `conversation_id` | | | Retrieve a Conversation |
| `retrieve_file.py` | `file_id` | | | Retrieve a File |
| `retrieve_file_content.py` | `file_id` | | | Retrieve the content of File |
| `retrieve_item.py` | `conversation_id` | `item_id` | | Retrieve an Item from a Conversation |
| `retrieve_model_response.py` | `response_id` | | | Retrieve a model Response |
| `retrieve_vector_store.py` | `vector_store_id` | | | Retrieve a Vector Store |
| `retrieve_vector_store_file.py` | `vector_store_id` | `file_id` | | Retrieve a File from a Vector Store |
| `retrieve_vector_store_file_content.py` | `vector_store_id` | `file_id` | | Retrieve the content of a File from a Vector Store |
| `update_conversation.py` | `conversation_id` | `metadata` | | Update a Conversation metadata |
| `upload_file.py` | `filename` | `path-to-file` | | Upload a File to the OpenAI platform |
| | Script | Parameter 1 | Parameter 2 | Parameter 3 | Purpose |
| --- | --------------------------------------- | ----------------- | --------------- | --------------- | ------------------------------------------------------------------------- |
| | `cancel_model_response.py` | `response_id` | | | Cancel a Response running in the background |
| | `create_conversation.py` | | | | Create a new Conversation |
| | `create_image.py` | `model_id` | `prompt` | `image.png` | Create an image based on the prompt description and/or the image provided |
| | `create_model_response.py` | `conversation_id` | `model_id` | `input_message` | Create a Response within a Conversation |
| | `create_text_item.py` | `conversation_id` | `input_message` | | Create a user input or instruction within a Conversation |
| | `create_vector_store.py` | | | | Create a Vector Store |
| | `create_vector_store_file.py` | `vector_store_id` | `file_id` | | Create a File in a Vector Store |
| | `delete_conversation.py` | `conversation_id` | | | Delete a Conversation |
| | `delete_file.py` | `file_id` | | | Delete a File |
| | `delete_item.py` | `conversation_id` | `item_id` | | Delete an Item (input or Response) from a Conversation |
| | `delete_model_response.py` | `response_id` | | | Delete a Response |
| | `delete_vector_store.py` | `vector_store_id` | | | Delete a Vector Store |
| | `delete_vector_store_file.py` | `vector_store_id` | `file_id` | | Delete a File from a Vector Store |
| | `list_files.py` | | | | List all uploaded Files |
| | `list_input_items.py` | `response_id` | | | List all input Items used to generate a Response |
| | `list_items.py` | `conversation_id` | | | List all Items (inputs or Responses) in a Conversation |
| | `list_vector_store_files.py` | `vector_store_id` | | | List all Files in a Vector Store |
| | `list_vector_stores.py` | | | | List all Vector Stores |
| | `modify_vector_store.py` | `vector_store_id` | `metadata` | | Update a Vector Store metadata |
| | `retrieve_conversation.py` | `conversation_id` | | | Retrieve a Conversation |
| | `retrieve_file.py` | `file_id` | | | Retrieve a File |
| | `retrieve_file_content.py` | `file_id` | | | Retrieve the content of File |
| | `retrieve_item.py` | `conversation_id` | `item_id` | | Retrieve an Item from a Conversation |
| | `retrieve_model_response.py` | `response_id` | | | Retrieve a model Response |
| | `retrieve_vector_store.py` | `vector_store_id` | | | Retrieve a Vector Store |
| | `retrieve_vector_store_file.py` | `vector_store_id` | `file_id` | | Retrieve a File from a Vector Store |
| | `retrieve_vector_store_file_content.py` | `vector_store_id` | `file_id` | | Retrieve the content of a File from a Vector Store |
| | `update_conversation.py` | `conversation_id` | `metadata` | | Update a Conversation metadata |
| | `update_vector_store_file.py` | `vector_store_id` | `file_id` | `attributes` | Update a File attributes |
| | `upload_file.py` | `filename` | `path-to-file` | | Upload a File to the OpenAI platform |
* To execute these scripts run `python3 <script.py> <parameter_1> ...`.

3
SECURITY.md
View file

@ -4,6 +4,9 @@
| Version | Supported |
| ------- | ------------------ |
| 0.5.x | :heavy_check_mark: |
| 0.4.x | :heavy_check_mark: |
| 0.3.x | :heavy_check_mark: |
| 0.2.x | :heavy_check_mark: |
| 0.1.x | :heavy_check_mark: |

2
config-sample.py
View file

@ -1,4 +1,4 @@
base_url = "https://api.openai.com/v1/"
secret_key = "YOUR-OPENAI-SECRET-KEY-HERE"
vector_store = "YOUR-VECTOR-STORE-ID-HERE"
vector_store = ["YOUR-VECTOR-STORE-IDs-HERE","SEPARATED-BY-COMMAS"]

57
create_image.py Normal file
View file

@ -0,0 +1,57 @@
from config import *
import requests
import json
import sys
import base64
from PIL import Image
from io import BytesIO
from datetime import datetime
def create_image(model,prompt,image_path=None):
# choose endpoint depending on whether an image is provided
if image_path:
url = base_url+"images/edits"
else:
url = base_url+"images/generations"
headers = {
'Authorization': 'Bearer '+secret_key,
}
date_time_string = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
if image_path:
# For edits, use multipart/form-data
data = {
"prompt": prompt,
"model": model
}
files = {
"image": open(image_path, "rb")
}
response = requests.post(url, headers=headers, data=data, files=files)
else:
# For generations, use JSON
payload = json.dumps({
"prompt": prompt,
"model": model
})
headers['Content-Type'] = 'application/json'
response = requests.post(url, headers=headers, data=payload)
if response.status_code != 200:
print(f"Error: {response.status_code} - {response.text}")
sys.exit(1)
# handle response data: both generation and edits return b64_json in data[0]
decoded_bytes = base64.b64decode(response.json()["data"][0]["b64_json"])
byte_stream = BytesIO(decoded_bytes)
image = Image.open(byte_stream)
image.save("./output_images/output-"+date_time_string+".png", "PNG")
print("Image ./output_images/output-"+date_time_string+".png has been generated.")
if __name__ == '__main__':
# usage: python create_image.py <model> <prompt> [image_path]
model = str(sys.argv[1]) if len(sys.argv) > 1 else ''
prompt = str(sys.argv[2]) if len(sys.argv) > 2 else ''
image_path = str(sys.argv[3]) if len(sys.argv) > 3 else None
create_image(model,prompt,image_path)

4
create_model_response.py
View file

@ -10,7 +10,7 @@ def create_model_response(conversation,model,message):
"model": model,
"tools": [
{"type": "web_search"},
{"type": "file_search", "vector_store_ids" :[vector_store]}
{"type": "file_search", "vector_store_ids" :vector_store}
],
"input": message,
"conversation": conversation
@ -23,5 +23,7 @@ def create_model_response(conversation,model,message):
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
print(response.json()["output"][-1]["content"][0]["text"])
if __name__ == '__main__':
create_model_response(str(sys.argv[1]),str(sys.argv[2]),str(sys.argv[3]))

22
modify_vector_store.py Normal file
View file

@ -0,0 +1,22 @@
from config import *
import requests
import json
import sys
def modify_vector_store(vector_store_id,metadata):
url = base_url+"vector_stores/"+vector_store_id
payload = json.dumps({
"metadata": json.loads(metadata)
})
headers = {
'Content-Type': 'application/json',
'Authorization': 'Bearer '+secret_key,
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
if __name__ == '__main__':
modify_vector_store(str(sys.argv[1]),str(sys.argv[2]))

0
output_images/__init__.py Normal file
View file

1
retrieve_item.py
View file

@ -13,6 +13,7 @@ def retrieve_item(conversation,message):
response = requests.request("GET", url, headers=headers, data=payload)
print(response.text)
print(response.json()["content"][0]["text"])
if __name__ == '__main__':

1
retrieve_model_response.py
View file

@ -13,6 +13,7 @@ def retrieve_model_response(response):
response = requests.request("GET", url, headers=headers, data=payload)
print(response.text)
print(response.json()["output"][-1]["content"][0]["text"])
if __name__ == '__main__':
retrieve_model_response(str(sys.argv[1]))

22
update_vector_store_file.py Normal file
View file

@ -0,0 +1,22 @@
from config import *
import requests
import json
import sys
def update_vector_store_file(vector_store_id,file_id,attributes):
url = base_url+"vector_stores/"+vector_store_id+"/files/"+file_id
payload = json.dumps({
"attributes": json.loads(attributes)
})
headers = {
'Content-Type': 'application/json',
'Authorization': 'Bearer '+secret_key,
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
if __name__ == '__main__':
update_vector_store_file(str(sys.argv[1]),str(sys.argv[2]),str(sys.argv[3]))