LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-11-29 16:43:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

(fix:attachment) dont calculate MIME again

Browse Source
This commit is contained in:
ManishMadan2882
2025-04-17 16:36:40 +05:30
parent c35d1cecfe
commit 335c21c48a
3 changed files with 80 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
application/llm/google_ai.py
View File

@@ -18,7 +18,7 @@ class GoogleLLM(BaseLLM):
def get_supported_attachment_types(self):
"""
Return a list of MIME types supported by Google Gemini for file uploads.
Returns:
list: List of supported MIME types
"""
@@ -30,35 +30,35 @@ class GoogleLLM(BaseLLM):
'image/webp',
'image/gif'
]
def prepare_messages_with_attachments(self, messages, attachments=None):
"""
Process attachments using Google AI's file API for more efficient handling.
Args:
messages (list): List of message dictionaries.
attachments (list): List of attachment dictionaries with content and metadata.
Returns:
list: Messages formatted with file references for Google AI API.
"""
if not attachments:
return messages
prepared_messages = messages.copy()
# Find the user message to attach files to the last one
user_message_index = None
for i in range(len(prepared_messages) - 1, -1, -1):
if prepared_messages[i].get("role") == "user":
user_message_index = i
break
if user_message_index is None:
user_message = {"role": "user", "content": []}
prepared_messages.append(user_message)
user_message_index = len(prepared_messages) - 1
if isinstance(prepared_messages[user_message_index].get("content"), str):
text_content = prepared_messages[user_message_index]["content"]
prepared_messages[user_message_index]["content"] = [
@@ -66,15 +66,11 @@ class GoogleLLM(BaseLLM):
]
elif not isinstance(prepared_messages[user_message_index].get("content"), list):
prepared_messages[user_message_index]["content"] = []
files = []
for attachment in attachments:
mime_type = attachment.get('mime_type')
if not mime_type:
file_path = attachment.get('path')
if file_path:
mime_type = mimetypes.guess_type(file_path)[0] or 'application/octet-stream'
if mime_type in self.get_supported_attachment_types():
try:
file_uri = self._upload_file_to_google(attachment)
@@ -84,53 +80,49 @@ class GoogleLLM(BaseLLM):
logging.error(f"GoogleLLM: Error uploading file: {e}")
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
"type": "text",
"text": f"[File could not be processed: {attachment.get('path', 'unknown')}]"
})
if files:
logging.info(f"GoogleLLM: Adding {len(files)} files to message")
prepared_messages[user_message_index]["content"].append({
"files": files
})
return prepared_messages
def _upload_file_to_google(self, attachment):
"""
Upload a file to Google AI and return the file URI.
Args:
attachment (dict): Attachment dictionary with path and metadata.
Returns:
str: Google AI file URI for the uploaded file.
"""
if 'google_file_uri' in attachment:
return attachment['google_file_uri']
file_path = attachment.get('path')
if not file_path:
raise ValueError("No file path provided in attachment")
if not os.path.isabs(file_path):
current_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
)
file_path = os.path.join(current_dir, "application", file_path)
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
mime_type = attachment.get('mime_type')
if not mime_type:
mime_type = mimetypes.guess_type(file_path)[0] or 'application/octet-stream'
try:
response = self.client.files.upload(file=file_path)
file_uri = response.uri
from application.core.mongo_db import MongoDB
mongo = MongoDB.get_client()
db = mongo["docsgpt"]
@@ -140,7 +132,7 @@ class GoogleLLM(BaseLLM):
{"_id": attachment['_id']},
{"$set": {"google_file_uri": file_uri}}
)
return file_uri
except Exception as e:
logging.error(f"Error uploading file to Google AI: {e}")
@@ -289,7 +281,7 @@ class GoogleLLM(BaseLLM):
if tools:
cleaned_tools = self._clean_tools_format(tools)
config.tools = cleaned_tools
# Check if we have both tools and file attachments
has_attachments = False
for message in messages:
@@ -299,16 +291,16 @@ class GoogleLLM(BaseLLM):
break
if has_attachments:
break
logging.info(f"GoogleLLM: Starting stream generation. Model: {model}, Messages: {json.dumps(messages, default=str)}, Has attachments: {has_attachments}")
response = client.models.generate_content_stream(
model=model,
contents=messages,
config=config,
)
for chunk in response:
if hasattr(chunk, "candidates") and chunk.candidates:
for candidate in chunk.candidates:

64
application/llm/openai.py
View File

@@ -149,7 +149,7 @@ class OpenAILLM(BaseLLM):
def get_supported_attachment_types(self):
"""
Return a list of MIME types supported by OpenAI for file uploads.
Returns:
list: List of supported MIME types
"""
@@ -161,35 +161,35 @@ class OpenAILLM(BaseLLM):
'image/webp',
'image/gif'
]
def prepare_messages_with_attachments(self, messages, attachments=None):
"""
Process attachments using OpenAI's file API for more efficient handling.
Args:
messages (list): List of message dictionaries.
attachments (list): List of attachment dictionaries with content and metadata.
Returns:
list: Messages formatted with file references for OpenAI API.
"""
if not attachments:
return messages
prepared_messages = messages.copy()
# Find the user message to attach file_id to the last one
user_message_index = None
for i in range(len(prepared_messages) - 1, -1, -1):
if prepared_messages[i].get("role") == "user":
user_message_index = i
break
if user_message_index is None:
user_message = {"role": "user", "content": []}
prepared_messages.append(user_message)
user_message_index = len(prepared_messages) - 1
if isinstance(prepared_messages[user_message_index].get("content"), str):
text_content = prepared_messages[user_message_index]["content"]
prepared_messages[user_message_index]["content"] = [
@@ -197,14 +197,10 @@ class OpenAILLM(BaseLLM):
]
elif not isinstance(prepared_messages[user_message_index].get("content"), list):
prepared_messages[user_message_index]["content"] = []
for attachment in attachments:
mime_type = attachment.get('mime_type')
if not mime_type:
file_path = attachment.get('path')
if file_path:
mime_type = mimetypes.guess_type(file_path)[0] or 'application/octet-stream'
if mime_type and mime_type.startswith('image/'):
try:
base64_image = self._get_base64_image(attachment)
@@ -218,14 +214,14 @@ class OpenAILLM(BaseLLM):
logging.error(f"Error processing image attachment: {e}")
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
"type": "text",
"text": f"[Image could not be processed: {attachment.get('path', 'unknown')}]"
})
# Handle PDFs using the file API
elif mime_type == 'application/pdf':
try:
file_id = self._upload_file_to_openai(attachment)
prepared_messages[user_message_index]["content"].append({
"type": "file",
"file": {"file_id": file_id}
@@ -234,80 +230,80 @@ class OpenAILLM(BaseLLM):
logging.error(f"Error uploading PDF to OpenAI: {e}")
if 'content' in attachment:
prepared_messages[user_message_index]["content"].append({
"type": "text",
"type": "text",
"text": f"File content:\n\n{attachment['content']}"
})
return prepared_messages
def _get_base64_image(self, attachment):
"""
Convert an image file to base64 encoding.
Args:
attachment (dict): Attachment dictionary with path and metadata.
Returns:
str: Base64-encoded image data.
"""
file_path = attachment.get('path')
if not file_path:
raise ValueError("No file path provided in attachment")
if not os.path.isabs(file_path):
current_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
)
file_path = os.path.join(current_dir, "application", file_path)
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
with open(file_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
def _upload_file_to_openai(self, attachment): ##pdfs
"""
Upload a file to OpenAI and return the file_id.
Args:
attachment (dict): Attachment dictionary with path and metadata.
Expected keys:
- path: Path to the file
- id: Optional MongoDB ID for caching
Returns:
str: OpenAI file_id for the uploaded file.
"""
import os
import logging
if 'openai_file_id' in attachment:
return attachment['openai_file_id']
file_path = attachment.get('path')
if not file_path:
raise ValueError("No file path provided in attachment")
if not os.path.isabs(file_path):
current_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
)
file_path = os.path.join(current_dir,"application", file_path)
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
try:
with open(file_path, 'rb') as file:
response = self.client.files.create(
file=file,
purpose="assistants"
)
file_id = response.id
from application.core.mongo_db import MongoDB
mongo = MongoDB.get_client()
db = mongo["docsgpt"]
@@ -317,7 +313,7 @@ class OpenAILLM(BaseLLM):
{"_id": attachment['_id']},
{"$set": {"openai_file_id": file_id}}
)
return file_id
except Exception as e:
logging.error(f"Error uploading file to OpenAI: {e}")
@@ -327,7 +323,7 @@ class OpenAILLM(BaseLLM):
class AzureOpenAILLM(OpenAILLM):
def __init__(
self, api_key, user_api_key, *args, **kwargs
self, api_key, user_api_key, *args, **kwargs
):
super().__init__(api_key)