303 lines
No EOL
14 KiB
Python
303 lines
No EOL
14 KiB
Python
import logging
|
|
import httpx
|
|
import os
|
|
from typing import Dict, Any, List, Union
|
|
from fastapi import HTTPException
|
|
from modules.shared.configuration import APP_CONFIG
|
|
from modules.aicore.aicoreBase import BaseConnectorAi
|
|
from modules.datamodels.datamodelAi import AiModel, ModelCapabilitiesEnum, PriorityEnum, ProcessingModeEnum, OperationTypeEnum
|
|
|
|
# Configure logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
def loadConfigData():
|
|
"""Load configuration data for Anthropic connector"""
|
|
return {
|
|
"apiKey": APP_CONFIG.get('Connector_AiAnthropic_API_SECRET'),
|
|
"apiUrl": APP_CONFIG.get('Connector_AiAnthropic_API_URL'),
|
|
"modelName": APP_CONFIG.get('Connector_AiAnthropic_MODEL_NAME'),
|
|
"temperature": float(APP_CONFIG.get('Connector_AiAnthropic_TEMPERATURE')),
|
|
}
|
|
|
|
class AiAnthropic(BaseConnectorAi):
|
|
"""Connector for communication with the Anthropic API."""
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
# Load configuration
|
|
self.config = loadConfigData()
|
|
self.apiKey = self.config["apiKey"]
|
|
self.apiUrl = self.config["apiUrl"]
|
|
self.modelName = self.config["modelName"]
|
|
|
|
# HttpClient for API calls
|
|
self.httpClient = httpx.AsyncClient(
|
|
timeout=120.0, # Longer timeout for complex requests
|
|
headers={
|
|
"x-api-key": self.apiKey,
|
|
"anthropic-version": "2023-06-01", # Anthropic API Version
|
|
"Content-Type": "application/json"
|
|
}
|
|
)
|
|
|
|
logger.info(f"Anthropic Connector initialized with model: {self.modelName}")
|
|
|
|
def getConnectorType(self) -> str:
|
|
"""Get the connector type identifier."""
|
|
return "anthropic"
|
|
|
|
def getModels(self) -> List[AiModel]:
|
|
"""Get all available Anthropic models."""
|
|
return [
|
|
AiModel(
|
|
name="anthropic_callAiBasic",
|
|
displayName="Claude 3.5 Sonnet",
|
|
connectorType="anthropic",
|
|
maxTokens=200000,
|
|
contextLength=200000,
|
|
costPer1kTokensInput=0.015,
|
|
costPer1kTokensOutput=0.075,
|
|
speedRating=7,
|
|
qualityRating=10,
|
|
capabilities=[ModelCapabilitiesEnum.TEXT_GENERATION, ModelCapabilitiesEnum.CHAT, ModelCapabilitiesEnum.REASONING, ModelCapabilitiesEnum.ANALYSIS],
|
|
functionCall=self.callAiBasic,
|
|
priority=PriorityEnum.QUALITY,
|
|
processingMode=ProcessingModeEnum.DETAILED,
|
|
operationTypes=[OperationTypeEnum.PLAN, OperationTypeEnum.ANALYSE],
|
|
version="claude-3-5-sonnet-20241022",
|
|
calculatePriceUsd=lambda processingTime, bytesSent, bytesReceived: (bytesSent / 4 / 1000) * 0.015 + (bytesReceived / 4 / 1000) * 0.075
|
|
),
|
|
AiModel(
|
|
name="anthropic_callAiImage",
|
|
displayName="Claude 3.5 Sonnet Vision",
|
|
connectorType="anthropic",
|
|
maxTokens=200000,
|
|
contextLength=200000,
|
|
costPer1kTokensInput=0.015,
|
|
costPer1kTokensOutput=0.075,
|
|
speedRating=7,
|
|
qualityRating=10,
|
|
capabilities=[ModelCapabilitiesEnum.IMAGE_ANALYSE, ModelCapabilitiesEnum.VISION, ModelCapabilitiesEnum.MULTIMODAL],
|
|
functionCall=self.callAiImage,
|
|
priority=PriorityEnum.QUALITY,
|
|
processingMode=ProcessingModeEnum.DETAILED,
|
|
operationTypes=[OperationTypeEnum.IMAGE_ANALYSE],
|
|
version="claude-3-5-sonnet-20241022",
|
|
calculatePriceUsd=lambda processingTime, bytesSent, bytesReceived: (bytesSent / 4 / 1000) * 0.015 + (bytesReceived / 4 / 1000) * 0.075
|
|
)
|
|
]
|
|
|
|
|
|
async def callAiBasic(self, messages: List[Dict[str, Any]], temperature: float = None, maxTokens: int = None) -> Dict[str, Any]:
|
|
"""
|
|
Calls the Anthropic API with the given messages.
|
|
|
|
Args:
|
|
messages: List of messages in OpenAI format (role, content)
|
|
temperature: Temperature for response generation (0.0-1.0)
|
|
maxTokens: Maximum number of tokens in the response
|
|
|
|
Returns:
|
|
The response in OpenAI format
|
|
|
|
Raises:
|
|
HTTPException: For errors in API communication
|
|
"""
|
|
try:
|
|
# Use parameters from configuration if none were overridden
|
|
if temperature is None:
|
|
temperature = self.config.get("temperature", 0.2)
|
|
|
|
# Don't set maxTokens from config - let the model use its full context length
|
|
# Our continuation system handles stopping early via prompt engineering
|
|
|
|
# Transform OpenAI-style messages to Anthropic format:
|
|
# - Move any 'system' role content to top-level 'system'
|
|
# - Keep only 'user'/'assistant' messages in the list
|
|
system_contents: List[str] = []
|
|
converted_messages: List[Dict[str, Any]] = []
|
|
for m in messages:
|
|
role = m.get("role")
|
|
content = m.get("content", "")
|
|
if role == "system":
|
|
# Collect system content; Anthropic expects top-level 'system'
|
|
if isinstance(content, list):
|
|
# Join text parts if provided as blocks
|
|
joined = "\n\n".join(
|
|
[
|
|
(part.get("text") if isinstance(part, dict) else str(part))
|
|
for part in content
|
|
]
|
|
)
|
|
system_contents.append(joined)
|
|
else:
|
|
system_contents.append(str(content))
|
|
continue
|
|
# For Anthropic, content can be a string; pass through strings, collapse blocks
|
|
if isinstance(content, list):
|
|
# Collapse to text if blocks are provided
|
|
collapsed = "\n\n".join(
|
|
[
|
|
(part.get("text") if isinstance(part, dict) else str(part))
|
|
for part in content
|
|
]
|
|
)
|
|
converted_messages.append({"role": role, "content": collapsed})
|
|
else:
|
|
converted_messages.append({"role": role, "content": content})
|
|
|
|
system_prompt = "\n\n".join([s for s in system_contents if s]) if system_contents else None
|
|
|
|
# Create Anthropic API payload
|
|
payload: Dict[str, Any] = {
|
|
"model": self.modelName,
|
|
"messages": converted_messages,
|
|
"temperature": temperature,
|
|
}
|
|
|
|
# Anthropic requires max_tokens - use provided value or throw error
|
|
if maxTokens is None:
|
|
raise ValueError("maxTokens must be provided for Anthropic API calls")
|
|
payload["max_tokens"] = maxTokens
|
|
if system_prompt:
|
|
payload["system"] = system_prompt
|
|
|
|
response = await self.httpClient.post(
|
|
self.apiUrl,
|
|
json=payload
|
|
)
|
|
|
|
if response.status_code != 200:
|
|
error_detail = f"Anthropic API error: {response.status_code} - {response.text}"
|
|
logger.error(error_detail)
|
|
|
|
# Provide more specific error messages based on status code
|
|
if response.status_code == 529:
|
|
error_message = "Anthropic API is currently overloaded. Please try again in a few minutes."
|
|
elif response.status_code == 429:
|
|
error_message = "Rate limit exceeded. Please wait before making another request."
|
|
elif response.status_code == 401:
|
|
error_message = "Invalid API key. Please check your Anthropic API configuration."
|
|
elif response.status_code == 400:
|
|
error_message = f"Invalid request to Anthropic API: {response.text}"
|
|
else:
|
|
error_message = f"Anthropic API error ({response.status_code}): {response.text}"
|
|
|
|
raise HTTPException(status_code=500, detail=error_message)
|
|
|
|
# Parse response
|
|
anthropicResponse = response.json()
|
|
|
|
# Extract content from response
|
|
content = ""
|
|
if "content" in anthropicResponse:
|
|
if isinstance(anthropicResponse["content"], list):
|
|
# Content is a list of parts (in newer API versions)
|
|
for part in anthropicResponse["content"]:
|
|
if part.get("type") == "text":
|
|
content += part.get("text", "")
|
|
else:
|
|
# Direct content as string (in older API versions)
|
|
content = anthropicResponse["content"]
|
|
|
|
# Debug logging for empty responses
|
|
if not content or content.strip() == "":
|
|
logger.warning(f"Anthropic API returned empty content. Full response: {anthropicResponse}")
|
|
content = "[Anthropic API returned empty response]"
|
|
|
|
# Return in OpenAI format
|
|
return {
|
|
"id": anthropicResponse.get("id", ""),
|
|
"object": "chat.completion",
|
|
"created": anthropicResponse.get("created", 0),
|
|
"model": anthropicResponse.get("model", self.modelName),
|
|
"choices": [
|
|
{
|
|
"message": {
|
|
"role": "assistant",
|
|
"content": content
|
|
},
|
|
"index": 0,
|
|
"finish_reason": "stop"
|
|
}
|
|
]
|
|
}
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error calling Anthropic API: {str(e)}")
|
|
raise HTTPException(status_code=500, detail=f"Error calling Anthropic API: {str(e)}")
|
|
|
|
async def callAiImage(self, prompt: str, imageData: Union[str, bytes], mimeType: str = None) -> str:
|
|
"""
|
|
Analyzes an image using Anthropic's vision capabilities.
|
|
|
|
Args:
|
|
imageData: Either a file path (str) or image data (bytes)
|
|
mimeType: The MIME type of the image (optional, only for binary data)
|
|
prompt: The prompt for analysis
|
|
|
|
Returns:
|
|
The analysis response as text
|
|
"""
|
|
try:
|
|
# Debug logging
|
|
logger.info(f"callAiImage called with imageData type: {type(imageData)}, length: {len(imageData) if imageData else 0}, mimeType: {mimeType}")
|
|
|
|
# Distinguish between file path and binary data
|
|
if isinstance(imageData, str):
|
|
# Check if it's base64 encoded data or a file path
|
|
if len(imageData) > 100 and not os.path.exists(imageData):
|
|
# It's likely base64 encoded data
|
|
logger.info("Treating imageData as base64 encoded string")
|
|
base64Data = imageData
|
|
if not mimeType:
|
|
mimeType = "image/png"
|
|
else:
|
|
# It's a file path - import filehandling only when needed
|
|
logger.info(f"Treating imageData as file path: {imageData}")
|
|
from modules import agentserviceFilemanager as fileHandler
|
|
base64Data, autoMimeType = fileHandler.encodeFileToBase64(imageData)
|
|
mimeType = mimeType or autoMimeType
|
|
else:
|
|
# It's binary data
|
|
logger.info("Treating imageData as binary data")
|
|
import base64
|
|
base64Data = base64.b64encode(imageData).decode('utf-8')
|
|
# MIME type must be specified for binary data
|
|
if not mimeType:
|
|
# Fallback to generic image type
|
|
mimeType = "image/png"
|
|
|
|
# Prepare the payload for the Vision API
|
|
messages = [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": prompt},
|
|
{
|
|
"type": "image_url",
|
|
"image_url": {
|
|
"url": f"data:{mimeType};base64,{base64Data}"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
|
|
# Use the existing callAiBasic function with the Vision model
|
|
response = await self.callAiBasic(messages)
|
|
|
|
# Extract and return content with proper error handling
|
|
try:
|
|
content = response["choices"][0]["message"]["content"]
|
|
if content is None or content.strip() == "":
|
|
return "[AI returned empty response for image analysis]"
|
|
return content
|
|
except (KeyError, IndexError, TypeError) as e:
|
|
logger.error(f"Error extracting content from AI response: {str(e)}")
|
|
logger.error(f"Response structure: {response}")
|
|
return f"[Error extracting AI response: {str(e)}]"
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error during image analysis: {str(e)}", exc_info=True)
|
|
return f"[Error during image analysis: {str(e)}]" |