gyt/opendan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

change /knowledge commands in shell

Browse Source
This commit is contained in:
tsukasa
2023-10-20 14:19:41 +08:00
parent 030077e4d3
commit d0b74545eb
13 changed files with 279 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/component/agent_manager/agent_manager.py
+15 -1
View File
@@ -1,9 +1,11 @@
import logging
import toml
import os
import runpy
from typing import Any, Callable, Dict, List, Optional, Union
from aios_kernel import AIAgent,AIAgentTemplete,AIStorage
from aios_kernel import AIAgent,AIAgentTemplete,AIStorage,Environment
from package_manager import PackageEnv,PackageEnvManager,PackageMediaInfo,PackageInstallTask
logger = logging.getLogger(__name__)
@@ -105,6 +107,18 @@ class AgentManager:
config_data = await config_file.read()
config = toml.loads(config_data)
result_agent = AIAgent()
if "owner_env" in config:
owner_env = config["owner_env"]
_, ext = os.path.splitext(owner_env)
if ext == ".py":
env_path = os.path.join(agent_media.full_path, owner_env)
owner_env = runpy.run_path(env_path)["init"]()
config["owner_env"] = owner_env
else:
owner_env = Environment.get_env_by_id(config["owner_env"])
config["owner_env"] = owner_env
if result_agent.load_from_config(config) is False:
logger.error(f"load agent from {agent_media} failed!")
return None
src/component/knowledge_manager/input/local_dir.py
+12 -9
View File
@@ -30,16 +30,19 @@ class KnowledgeDirSource:
return await f.read()
async def next(self):
journals = self.env.journal.latest_journals(1)
from_time = 0
if len(journals) == 1:
latest_journal = journals[0]
if latest_journal.is_finish():
yield None
from_time = os.path.getctime(latest_journal.get_input())
if os.path.getmtime(self.path()) <= from_time:
yield (None, None)
while True:
journals = self.env.journal.latest_journals(1)
from_time = 0
if len(journals) == 1:
latest_journal = journals[0]
if latest_journal.is_finish():
yield None
continue
from_time = os.path.getctime(latest_journal.get_input())
if os.path.getmtime(self.path()) <= from_time:
yield (None, None)
continue
file_pathes = sorted(os.listdir(self.path()), key=lambda x: os.path.getctime(os.path.join(self.path(), x)))
for rel_path in file_pathes:
file_path = os.path.join(self.path(), rel_path)
src/component/knowledge_manager/pipeline.py
+18 -2
View File
@@ -4,7 +4,17 @@ import toml
import asyncio
from knowledge import KnowledgePipelineEnvironment, KnowledgePipeline
class KnowledgePipelineManager:
@classmethod
def initial(cls, root_dir: str):
cls._instance = KnowledgePipelineManager(root_dir)
return cls._instance
@classmethod
def get_instance(cls):
return cls._instance
def __init__(self, root_dir: str):
self.root_dir = root_dir
self.input_modules = {}
@@ -32,7 +42,7 @@ class KnowledgePipelineManager:
input_module = config["input"]["module"]
_, ext = os.path.splitext(input_module)
if ext == ".py":
input_module = os.path.abspath(path, input_module)
input_module = os.path.join(path, input_module)
input_init = runpy.run_path(input_module)["init"]
else:
input_init = self.input_modules.get(input_module)
@@ -41,7 +51,7 @@ class KnowledgePipelineManager:
parser_module = config["parser"]["module"]
_, ext = os.path.splitext(parser_module)
if ext == ".py":
parser_module = os.path.abspath(path, parser_module)
parser_module = os.path.join(path, parser_module)
parser_init = runpy.run_path(parser_module)["init"]
else:
parser_init = self.parser_modules.get(parser_module)
@@ -54,6 +64,12 @@ class KnowledgePipelineManager:
self.pipelines["names"][name] = pipeline
self.pipelines["running"].append(pipeline)
def get_pipelines(self) -> [KnowledgePipeline]:
return self.pipelines["running"]
def get_pipeline(self, name: str) -> KnowledgePipeline:
return self.pipelines["names"].get(name)
async def run(self):
while True:
for pipeline in self.pipelines["running"]:
src/component/knowledge_manager/query/embedding.py
-82
View File
@@ -1,82 +0,0 @@
class KnowledgeEnvironment(Environment):
def __init__(self, env_id: str) -> None:
super().__init__(env_id)
query_param = {
"tokens": "key words to query",
"types": "prefered knowledge types, one or more of [text, image]",
"index": "index of query result"
}
self.add_ai_function(SimpleAIFunction("query_knowledge",
"vector query content from local knowledge base",
self._query,
query_param))
async def query_objects(self, tokens: str, types: list[str], topk: int) -> [ObjectID]:
texts = []
if "text" in types:
vector = await self.compute_kernel.do_text_embedding(tokens, self._default_text_model)
texts = await self.store.get_vector_store(self._default_text_model).query(vector, topk)
images = []
if "image" in types:
vector = await self.compute_kernel.do_text_embedding(tokens, self._default_image_model)
images = await self.store.get_vector_store(self._default_image_model).query(vector, topk)
return texts + images
def tokens_from_objects(self, object_ids: [ObjectID]) -> list[str]:
results = dict()
for object_id in object_ids:
parents = self.store.get_relation_store().get_related_root_objects(object_id)
# last parent is the root object
root_object_id = parents[0] if parents else object_id
logging.info(f"object_id: {str(object_id)} root_object_id: {str(root_object_id)}")
if str(root_object_id) in results:
results[str(root_object_id)].append(object_id)
else:
results[str(root_object_id)] = [root_object_id, object_id]
content = ""
result_desc = []
for result in results.values():
# first element in result is the root object
root_object_id = result[0]
if root_object_id.get_object_type() == ObjectType.Email:
email = self.load_object(root_object_id)
desc = email.get_desc()
desc["type"] = "email"
desc["contents"] = []
result_desc.append(desc)
upper_list = desc["contents"]
result = result[1:]
else:
upper_list = result_desc
for object_id in result:
if object_id.get_object_type() == ObjectType.Chunk:
upper_list.append({"type": "text", "content": self.store.get_chunk_reader().get_chunk(object_id).read().decode("utf-8")})
if object_id.get_object_type() == ObjectType.Image:
# image = self.load_object(object_id)
desc = dict()
desc["id"] = str(object_id)
desc["type"] = "image"
upper_list.append(desc)
if object_id.get_object_type() == ObjectType.Video:
video = self.load_object(object_id)
desc = video.get_desc()
desc["type"] = "video"
upper_list.append(desc)
else:
pass
content += json.dumps(result_desc)
content += ".\n"
return content
async def _query(self, tokens: str, types: list[str] = ["text"], index: str=0):
index = int(index)
object_ids = await KnowledgeBase().query_objects(tokens, types, 4)
if len(object_ids) <= index:
return "*** I have no more information for your reference.\n"
else:
content = "*** I have provided the following known information for your reference with json format:\n"
return content + KnowledgeBase().tokens_from_objects(object_ids[index:index+1])