agent/openai:nits

examples/agent/README.md

@@ -76,7 +76,7 @@ This example relies on the new [OpenAI compatibility server](../openai).
   agent.py  →  examples.openai  →  server.cpp
             →  safe_tools.py
             → ( run_sandboxed_tools.sh :  Docker  →  fastify.py )  →  unsafe_tools.py  →  code interpreter, etc...
-``` 
+```
 
 The agent can use tools written in Python, or (soon) exposed under OpenAPI endpoints. Only has standard Python deps (e.g. no langchain)
 

examples/agent/agent.py

@@ -128,7 +128,7 @@ def main(
     max_iterations: Optional[int] = 10,
     std_tools: Optional[bool] = False,
     auth: Optional[str] = None,
-    allow_parallel_calls: Optional[bool] = False,
+    parallel_calls: Optional[bool] = True,
     verbose: bool = False,
 
     model: Annotated[Optional[Path], typer.Option("--model", "-m")] = "models/7B/ggml-model-f16.gguf",
@@ -174,14 +174,14 @@ def main(
             "python", "-m", "examples.openai.server",
             "--model", model,
             *(['--verbose'] if verbose else []),
-            *(['--allow-parallel-calls'] if allow_parallel_calls else []),
+            *(['--parallel-calls'] if parallel_calls else []),
             *(['--context-length={context_length}'] if context_length else []),
             *([])
         ]
         server_process = subprocess.Popen(cmd, stdout=sys.stderr)
         atexit.register(server_process.kill)
         sleep(5)
-    
+
     tool_functions = []
     types = {}
     for f in tools:
@@ -195,7 +195,7 @@ def main(
 
     if std_tools:
         tool_functions.extend(collect_functions(StandardTools))
-    
+
     response_model = None#str
     if format:
         if format in types:
@@ -207,8 +207,8 @@ def main(
                 response_model = json.loads(format)
             except:
                 response_model = eval(format)
-    
-    
+
+
     result = completion_with_tool_usage(
         model="...",
         endpoint=endpoint,

examples/agent/fastify.py

@@ -41,4 +41,4 @@ def main(files: List[str], host: str = '0.0.0.0', port: int = 8000):
 
 if __name__ == '__main__':
     typer.run(main)
-    
+

examples/agent/run_sandboxed_tools.sh

@@ -11,7 +11,7 @@ script="$( realpath "$1" )"
 script_folder="$(dirname "$script")"
 shift 1
 
-function cleanup {      
+function cleanup {
   rm -rf "$BUILD_DIR"
   echo "Deleted $BUILD_DIR"
 }

examples/agent/tools/std_tools.py

@@ -1,15 +1,11 @@
-import atexit
 from datetime import date
 import datetime
+from pydantic import BaseModel
 import subprocess
 import sys
-from time import sleep
 import time
 import typer
-from pydantic import BaseModel, Json, TypeAdapter
-from annotated_types import MinLen
-from typing import Annotated, Callable, List, Union, Literal, Optional, Type, get_args, get_origin
-import json, requests
+from typing import Union, Optional
 
 class Duration(BaseModel):
     seconds: Optional[int] = None
@@ -50,7 +46,7 @@ def __call__(self):
         sys.stderr.write(f"Waiting for {days} days and {seconds} seconds until {d}...\n")
         time.sleep(days * 86400 + seconds)
         sys.stderr.write(f"Reached the target date: {self.until}\n")
-        
+
 
 class StandardTools:
 
@@ -61,15 +57,15 @@ def ask_user(question: str) -> str:
             This allows getting additional information, requesting disambiguation, etc.
         '''
         return typer.prompt(question)
-    
+
     @staticmethod
     def wait(_for: Union[WaitForDuration, WaitForDate]) -> None:
         '''
             Wait for a certain amount of time before continuing.
             This can be used to wait for a specific duration or until a specific date.
         '''
         return _for()
-    
+
     @staticmethod
     def say_out_loud(something: str) -> str:
         """

examples/openai/README.md

@@ -34,7 +34,7 @@ The new [examples/openai/server.py](./server.py):
           }
           // Where T is the output JSON schema, or 'any'
         ```
-      
+
         - Option to publicise schemas to models as TypeScript signatures (as for Functionary) or JSON schema.
 
         - Supports models that require user/assistant alternance (like Mixtral Instruct) by merging system messages into user messages.
@@ -175,7 +175,7 @@ curl http://localhost:8080/v1/chat/completions \
 - Evaluate options for session caching
 
     - Pass session id & store / read from file?
-    
+
     - Support parent session ids for trees of thought?
 
     - Support precaching long prompts from CLI / read session files?
@@ -186,4 +186,4 @@ curl http://localhost:8080/v1/chat/completions \
 
     - Remove non-Python json-schema-to-grammar versions
 
-    - Reach out to frameworks to advertise new option. 
+    - Reach out to frameworks to advertise new option.

examples/openai/llama_cpp_server_api.py

@@ -1,28 +1,12 @@
 from typing import Optional
-from pydantic import BaseModel, Json
+from pydantic import Json
 
-class LlamaCppServerCompletionRequest(BaseModel):
+from examples.openai.api import LlamaCppParams
+
+class LlamaCppServerCompletionRequest(LlamaCppParams):
     prompt: str
     stream: Optional[bool] = None
     cache_prompt: Optional[bool] = None
-    n_predict: Optional[int] = None
-    top_k: Optional[int] = None
-    top_p: Optional[float] = None
-    min_p: Optional[float] = None
-    tfs_z: Optional[float] = None
-    typical_p: Optional[float] = None
-    temperature: Optional[float] = None
-    dynatemp_range: Optional[float] = None
-    dynatemp_exponent: Optional[float] = None
-    repeat_last_n: Optional[int] = None
-    repeat_penalty: Optional[float] = None
-    frequency_penalty: Optional[float] = None
-    presence_penalty: Optional[float] = None
-    mirostat: Optional[bool] = None
-    mirostat_tau: Optional[float] = None
-    mirostat_eta: Optional[float] = None
-    penalize_nl: Optional[bool] = None
-    n_keep: Optional[int] = None
-    seed: Optional[int] = None
+
     grammar: Optional[str] = None
     json_schema: Optional[Json] = None