LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-11-30 00:53:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: context compression

Browse Source
This commit is contained in:
Alex
2025-11-23 18:35:51 +00:00
parent 9e58eb02b3
commit 3737beb2ba
28 changed files with 5393 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
application/core/model_configs.py
View File

@@ -29,63 +29,29 @@ GOOGLE_ATTACHMENTS = [
OPENAI_MODELS = [
AvailableModel(
id="gpt-4o",
id="gpt-5.1",
provider=ModelProvider.OPENAI,
display_name="GPT-4 Omni",
description="Latest and most capable model",
display_name="GPT-5.1",
description="Flagship model with enhanced reasoning, coding, and agentic capabilities",
capabilities=ModelCapabilities(
supports_tools=True,
supports_structured_output=True,
supported_attachment_types=OPENAI_ATTACHMENTS,
context_window=128000,
context_window=400000,
),
),
AvailableModel(
id="gpt-4o-mini",
id="gpt-5-mini",
provider=ModelProvider.OPENAI,
display_name="GPT-4 Omni Mini",
description="Fast and efficient",
display_name="GPT-5 Mini",
description="Faster, cost-effective variant of GPT-5.1",
capabilities=ModelCapabilities(
supports_tools=True,
supports_structured_output=True,
supported_attachment_types=OPENAI_ATTACHMENTS,
context_window=128000,
context_window=400000,
),
),
AvailableModel(
id="gpt-4-turbo",
provider=ModelProvider.OPENAI,
display_name="GPT-4 Turbo",
description="Fast GPT-4 with 128k context",
capabilities=ModelCapabilities(
supports_tools=True,
supports_structured_output=True,
supported_attachment_types=OPENAI_ATTACHMENTS,
context_window=128000,
),
),
AvailableModel(
id="gpt-4",
provider=ModelProvider.OPENAI,
display_name="GPT-4",
description="Most capable model",
capabilities=ModelCapabilities(
supports_tools=True,
supports_structured_output=True,
supported_attachment_types=OPENAI_ATTACHMENTS,
context_window=8192,
),
),
AvailableModel(
id="gpt-3.5-turbo",
provider=ModelProvider.OPENAI,
display_name="GPT-3.5 Turbo",
description="Fast and cost-effective",
capabilities=ModelCapabilities(
supports_tools=True,
context_window=4096,
),
),
)
]
@@ -159,15 +125,15 @@ GOOGLE_MODELS = [
),
),
AvailableModel(
id="gemini-2.5-pro",
id="gemini-3-pro-preview",
provider=ModelProvider.GOOGLE,
display_name="Gemini 2.5 Pro",
display_name="Gemini 3 Pro",
description="Most capable Gemini model",
capabilities=ModelCapabilities(
supports_tools=True,
supports_structured_output=True,
supported_attachment_types=GOOGLE_ATTACHMENTS,
context_window=2000000,
context_window=20000, # Set low for testing compression
),
),
]

7
application/core/settings.py
View File

@@ -144,6 +144,13 @@ class Settings(BaseSettings):
# Tool pre-fetch settings
ENABLE_TOOL_PREFETCH: bool = True
# Conversation Compression Settings
ENABLE_CONVERSATION_COMPRESSION: bool = True
COMPRESSION_THRESHOLD_PERCENTAGE: float = 0.8 # Trigger at 80% of context
COMPRESSION_MODEL_OVERRIDE: Optional[str] = None # Use different model for compression
COMPRESSION_PROMPT_VERSION: str = "v1.0" # Track prompt iterations
COMPRESSION_MAX_HISTORY_POINTS: int = 3 # Keep only last N compression points to prevent DB bloat
path = Path(__file__).parent.parent.absolute()
settings = Settings(_env_file=path.joinpath(".env"), _env_file_encoding="utf-8")