AIGC（生成式AI）试用 44 -- 个人知识库 DocsGpt
AIGC（生成式AI）试用 44 -- 个人知识库 DocsGpt
·
一切从DocsGPT的API调用开始。
1. Python API调用
(千问) 提问：python调用API方法
Python 中调用 API（通常指 HTTP 接口，如 RESTful API）最常用的方式是使用 requests 库。
| 场景 | 方法 |
|---|---|
| 获取数据 | requests.get(url, params=...) |
| 提交 JSON | requests.post(url, json=...) |
| 上传文件 | requests.post(url, files=...) |
| 带 Token | headers={"Authorization": "Bearer xxx"} |
| 安全健壮 | 加 timeout + try-except + raise_for_status() |
import requests
# GET方法
Parameters = {}
response = requests.get(GET_URL, Parameters)
# return: response.status_code, response.text
# POST方法
Data = {} # headers, json
response = requests.post(post_URL, Data, headers)2. 调用DocsGPT --
| answer | Answer related operations |
| analytics | Analytics and reporting operations |
| attachments | File attachments and media operations |
| conversations | Conversation management operations |
| models | Available models |
| agents | Agent management operations |
| prompts | Prompt management operations |
| sharing | Conversation sharing operations |
| sources | Source document management operations |
| tools | Tool management operations |
| connectors | Connector operations |
- payload Parameters -- 待确认、实际验证
| question | 用户提问或输入 |
| api_key | agent API key |
| chunk | 上下文数量，指定从向量数据库中检索多少个相关文本片段（chunks）作为上下文 |
| retriever | 检索器类型（即如何从文档中查找相关信息）: default;parent_document, 先子块再父文档;multi_query |
| temperature | 控制大语言模型（LLM）生成文本的随机性/创造性，0.0~2.0，确定~随机，注意幻觉的产生 |
| passthrough | 是否启用 “直通模式”：True，不查RAG文档直接提问；执行RAG流程（检索+提问） |
| history | 对话历史, JSON |
| model_id | 指定LLM模型类型 |
| prompt_id | local 或 prompt_id，本地无需验证 |
| isNoneDoc | False，查看RAG文档 |
| save_conversation | True: 保留对话历史 |
| tools | LLM 可调用的外部函数/插件 |
| attachments | 上传附件，知识库补充 |
| json_schema | LLM 输出必须符合的 JSON 结构，用于强制格式化响应 |
- POST： api/answer
import requests
purl = "http://localhost:7091/api/answer"
payload = {
"question": "who are you?",
## "history": [string],
## "conversation_id": "string",
"prompt_id": "default",
"chunks": 2,
"retriever": "",
## "api_key": "string",
"active_docs": "",
"isNoneDoc": True,
"save_conversation": True,
"model_id": "docsgpt-local",
"passthrough": {},
"temperature": 0.0,
"top_k": 5
}
response = requests.post(purl, json=payload)
if response.status_code == 200:
result = response.json()
print(f">> Answer: {result.get('answer')}, \n>> StatusCode: {response.status_code}, \n>> Text: {response.text}")
else:
print(f"Fail: {response.status_code}, {response.text}")
###############
>> Answer: I am your DocsGPT. I am an AI assistant designed to provide helpful and accurate responses, assist with documentation, and engage in meaningful conversations. I aim to be proactive and helpful in answering your questions based on both your input and any additional context provided.,
>> StatusCode: 200,
>> Text: {
"answer": "I am your DocsGPT. I am an AI assistant designed to provide helpful and accurate responses, assist with documentation, and engage in meaningful conversations. I aim to be proactive and helpful in answering your questions based on both your input and any additional context provided.",
"conversation_id": "6967afe8066b58e22408544f",
"sources": [],
"thought": "",
"tool_calls": []
}
################ Error List
--> "model_id": "deepseek-r1:1.5b",
Fail: 500, {
"error": "Invalid model_id 'deepseek-r1:1.5b'. Available models: docsgpt-local, gpt-5.1, gpt-5-mini"
}
--> not set "model_id"
>> Answer: None,
>> StatusCode: 200,
>> Text: {
"answer": null,
"conversation_id": null,
"sources": null,
"thought": "Please try again later. We apologize for any inconvenience.",
"tool_calls": null
}
--> "history": [],
Fail: 500, {
"error": "the JSON object must be str, bytes or bytearray, not list"
}
--> "conversation_id": "string",
Fail: 500, {
"error": "Conversation not found or unauthorized"
}- POST： stream
import requests, json
purl = "http://localhost:7091/stream"
payload = {
"question": "who are you?",
## "history": ["string"],
## "conversation_id": "",
## "prompt_id": "default",
## "chunks": 2,
## "retriever": "string",
#### "api_key": "string",
## "active_docs": "string",
## "isNoneDoc": True,
## "index": 0,
## "save_conversation": True,
"model_id": "docsgpt-local",
## "attachments": ["string"],
## "passthrough": {}
}
response = requests.post(purl, json=payload)
if response.status_code == 200:
result = response.iter_lines()
answer= ""
jid = ""
for line in result:
if line:
text = line.decode('utf-8', errors='ignore')
data = text.split("data:")[1].strip()
jdata = json.loads(data)
if jdata.get("answer"):
answer = answer + jdata["answer"]
if jdata.get("id"):
jid = jdata["id"]
print(f">> Answer: {answer}, \n>> StatusCode: {response.status_code}, \n>> ID: {jid}")
else:
print(f"Fail: {response.status_code}, {jid}")
##########################
>> Answer: I am DocsGPT, an AI assistant designed to help you with documents and answer questions. I analyze uploaded documents (PDF, DOCX, TXT, etc.) to provide contextualized answers. I can also use available tools, like APIs, to fetch real-time data when needed. My goal is to deliver accurate, relevant, and actionable responses.,
>> StatusCode: 200,
>> ID: 696a382be304c4e05c085443
########################## Error List
--> <Response [200]> <class 'requests.models.Response'>
result = response.iter_lines()
--> json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
line: b'data: {"type": "id", "id": "696a3ab5e304c4e05c085453"}'
text = line.decode('utf-8', errors='ignore')
text: data: {"type": "id", "id": "696a3ab5e304c4e05c085453"}
- POST： api/create_prompt
import requests, json
curl = "http://localhost:7091/api/create_prompt"
gsurl = "http://localhost:7091/api/get_prompts"
gurl = "http://localhost:7091/api/get_single_prompt"
purl = "http://localhost:7091/stream"
payload = {
"content": "",
"name": "who are you?",
}
response = requests.post(curl, json=payload)
result = response.json()
payload = {
"question": "你是谁？来自哪里？能做什么？",
## "history": ["string"],
## "conversation_id": "",
"prompt_id": f"{result.get("id")}",
## "chunks": 2,
## "retriever": "string",
#### "api_key": "string",
## "active_docs": "string",
## "isNoneDoc": True,
## "index": 0,
## "save_conversation": True,
"model_id": "docsgpt-local",
## "attachments": ["string"],
## "passthrough": {}
}
response = requests.post(purl, json=payload)
if response.status_code == 200:
result = response.iter_lines()
answer= ""
jid = ""
for line in result:
if line:
text = line.decode('utf-8', errors='ignore')
data = text.split("data:")[1].strip()
jdata = json.loads(data)
if jdata.get("answer"):
answer = answer + jdata["answer"]
if jdata.get("id"):
jid = jdata["id"]
print(f">> Answer: {answer}, \n>> StatusCode: {response.status_code}, \n>> ID: {jid}")
else:
print(f"Fail: {response.status_code}")
#############################################
>> Answer: 我是 **Kimi**，由 **月之暗面科技有限公司**（Moonshot AI）训练的大语言模型。我出生于 **2023 年 10 月**，知识截止于 **2025 年 4 月**。
我擅长用自然流畅的语言和你交流，能做的事情包括但不限于：
- 回答各类知识和信息咨询
- 帮你阅读、总结长文档或网页内容
- 协助写作、翻译、润色文本
- 帮你写代码、解释代码、调试程序
- 制定计划、提供建议、模拟对话等
你可以随时向我提问，我会尽力帮你解决。,
>> StatusCode: 200,
>> ID: 696cf48bbb06b2fb690853c9
- POST：api/create_agent
import requests, json
purl = "http://localhost:7091/api/create_agent"
payload = {
"name": "NewAgent",
"description": "This is new angent",
## "image": {},
"source": "Default",
## "sources": [
## "string"
## ],
"chunks": 2,
"retriever": "string",
"prompt_id": "default",
## "tools": [
## "string"
## ],
"agent_type": "Classic",
"status": "published",
## "json_schema": {},
## "limited_token_mode": true,
## "token_limit": 0,
## "limited_request_mode": true,
## "request_limit": 0,
## "models": [
## "string"
## ],
"default_model_id": "docsgpt-local",
}
response = requests.post(purl, json=payload, stream=True)
if response.status_code == 200:
result = response.json()
print("result: ", result)
print(result)
print(f">> Answer: {result.get('answer')}, \n>> StatusCode: {response.status_code}, \n>> Text: {response.text}")
else:
print(f"Fail: {response.status_code}, {response.text}")
#####################################
Fail: 201, {
"id": "696cdd93e304c4e05c0854eb",
"key": "7524f0b4-e4ec-4cc6-9cd5-faa2869274ca"
########################## Error List
--> Fail: 400, {
"message": "Status must be either 'draft' or 'published'",
"success": false
}
--> Fail: 400, {
"message": "Either 'source' or 'sources' field is required for published agents",
"success": false
}
--> Fail: 400, {
"message": "Missing required fields: description, chunks, retriever, prompt_id, agent_type",
"success": false
}- Get：api/get_agent(s)
import requests, json
purl = "http://localhost:7091/api/delete_agent"
gurl = "http://localhost:7091/api/get_agent"
gsurl = "http://localhost:7091/api/get_agents"
response = requests.get(gsurl)
result = response.json()
for gid in result:
response = requests.get(gurl+"?id="+gid.get("id"))
result = response.json()
print("---------->Agent: ")
for agent in result:
print(agent,": ",result[agent])
###################################
---------->Agent:
agent_type : classic
chunks : 2
created_at : Wed, 31 Dec 2025 14:09:38 GMT
default_model_id :
description : pic word recognize
id : 69552ea240d00b40db5f1543
image :
json_schema : None
key : 8d64...4b85
last_used_at : Wed, 31 Dec 2025 15:50:50 GMT
limited_request_mode : False
limited_token_mode : False
models : []
name : PicWordReg
pinned : False
prompt_id : 69552e8040d00b40db5f1542
request_limit : 0
retriever :
shared : True
shared_metadata : {'shared_at': 'Wed, 31 Dec 2025 14:09:46 GMT', 'shared_by': ''}
shared_token : ml7EmEkaTFYeHh_QAkWOnhvqsN5wEpkpKEwbdeSM3Qk
source :
sources : []
status : published
token_limit : 0
tool_details : []
tools : []
updated_at : Wed, 31 Dec 2025 14:09:38 GMT
3. Issues
- api/answer, stream的区别
| 特性 | 非流式（如 /api/answer） |
流式（stream=true） |
|---|---|---|
| 响应方式 | 一次性返回完整答案 | 逐字/逐 token 返回 |
| 等待时间 | 需等待模型生成完整内容后才返回（延迟高） | 首字几乎立即返回（延迟低） |
| 网络传输 | 单次 HTTP 响应 | 持续的 HTTP 流（如 SSE、Chunked Transfer） |
| 用户体验 | “转圈 → 突然全部出现” | “打字机效果”，边生成边显示 |
| 资源占用 | 服务端需缓存完整结果 | 服务端边生成边发送，内存更省 |
| 适用场景 | 后台处理、批量任务 | 聊天界面、实时交互 |
| 效果对比 |
用户点击“发送” 等待 5 秒（模型思考 + 生成） 屏幕突然显示完整回答 |
用户点击“发送” 0.5 秒后第一个字出现 后续文字像打字机一样逐字输出 |
| 场景 | 后台自动化任务（如生成报告） API 被其他程序调用（非人交互） |
Web 聊天界面（如微信、网页助手） 移动 App 聊天 |
| 简单、适合机器调用，但用户体验差 | 复杂一点，但提供实时反馈，是聊天类应用的标准做法。 |
4. DocsGPT Port
- Port: 5173, DocsGPT running
setup.ps1: Write-ColorText "DocsGPT is running at http://localhost:5173"
DocsGPT-main\application\app.py: redirect("http://localhost:5173") - Port: 11434, AI Model
.env: OPENAI_BASE_URL=http://host.docker.internal:11434
deployment\optional\docker-compose.optional.ollama-cpu.yaml: ports: - "11434:11434" - Port: 7091, API access
deployment\docker-compose-local.yaml: VITE_API_HOST=http://localhost:7091
4. DocsGPT environment
- ollama
ollama list ########################################################## NAME ID SIZE MODIFIED deepseek-r1:1.5b a42b25d8c10a 1.1 GB 11 months ago - Docker
docker --version docker-compose --version docker system info ########################################################## Docker version 29.1.3, build f52814d Docker Compose version v2.40.3-desktop.1 Client: Version: 29.1.3 Context: desktop-linux ...... Server: Containers: 9 Running: 6 wsl --list --verbose ########################################################## NAME STATE VERSION * docker-desktop Running 2 docker images ########################################################## i Info → U In Use IMAGE ID DISK USAGE CONTENT SIZE EXTRA arc53/docsgpt-fe:develop 89a336ecda3a 973MB 236MB U arc53/docsgpt:develop f49f4d12dd3c 12GB 4.28GB U docsgpt-oss-backend:latest 61116975e170 15.2GB 5.45GB U docsgpt-oss-frontend:latest 7bdb0c8f98ed 973MB 236MB U docsgpt-oss-worker:latest 9c3988fdb2f3 15.2GB 5.45GB U mongo:6 03cda579c8ca 1.06GB 273MB U ollama/ollama:latest 2c9595c555fd 6.14GB 2.17GB U redis:6-alpine 37e002448575 45.1MB 12.9MB U
参考：
有“AI”的1024 = 2048，欢迎大家加入2048 AI社区
更多推荐
18
0- 0
已为社区贡献26条内容
所有评论(0)