- English | [中文](./README_CHS.md) | [繁體中文](./README_CHT.md) | [Français](./README_FR.md) | [日本語](./README_JP.md) | [Português (Brasil)](./README_PTBR.md)
+ English | [中文](./README_CHS.md) | [繁體中文](./README_CHT.md) | [Français](./README_FR.md) | [日本語](./README_JP.md) | [Português (Brasil)](./README_PTBR.md) | [Español](./README_ES.md)
*A **100% local alternative to Manus AI**, this voice-enabled AI assistant autonomously browses the web, writes code, and plans tasks while keeping all data on your device. Tailored for local reasoning models, it runs entirely on your hardware, ensuring complete privacy and zero cloud dependency.*
@@ -167,7 +167,7 @@ Next step: [Start services and run AgenticSeek](#Start-services-and-Run)
*See the **Run with an API** section if your hardware can't run deepseek locally*
-*See the **Config** section for detailled config file explanation.*
+*See the **Config** section for detailed config file explanation.*
---
@@ -206,7 +206,7 @@ Next step: [Start services and run AgenticSeek](#Start-services-and-Run)
*See the **Known issues** section if you are having issues*
-*See the **Config** section for detailled config file explanation.*
+*See the **Config** section for detailed config file explanation.*
---
diff --git a/api.py b/api.py
index 9e70a4a..425fc72 100755
--- a/api.py
+++ b/api.py
@@ -255,5 +255,5 @@ if __name__ == "__main__":
if envport:
port = int(envport)
else:
- port = 8000
- uvicorn.run(api, host="0.0.0.0", port=8000)
\ No newline at end of file
+ port = 7777
+ uvicorn.run(api, host="0.0.0.0", port=7777)
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
index 5cd548d..f66f3fd 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -65,7 +65,7 @@ services:
environment:
- NODE_ENV=development
- CHOKIDAR_USEPOLLING=true
- - REACT_APP_BACKEND_URL=http://0.0.0.0:${BACKEND_PORT:-8000}
+ - REACT_APP_BACKEND_URL=http://host.docker.internal:${BACKEND_PORT:-7777}
networks:
- agentic-seek-net
@@ -88,6 +88,7 @@ services:
- SEARXNG_URL=${SEARXNG_BASE_URL:-http://searxng:8080}
- REDIS_URL=${REDIS_BASE_URL:-redis://redis:6379/0}
- WORK_DIR=/opt/workspace
+ - BACKEND_PORT=${BACKEND_PORT}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY}
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
@@ -96,7 +97,8 @@ services:
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
- HUGGINGFACE_API_KEY=${HUGGINGFACE_API_KEY}
- DSK_DEEPSEEK_API_KEY=${DSK_DEEPSEEK_API_KEY}
- network_mode: "host"
+ networks:
+ - agentic-seek-net
volumes:
redis-data:
diff --git a/frontend/agentic-seek-front/src/App.js b/frontend/agentic-seek-front/src/App.js
index ed64d08..b456e79 100644
--- a/frontend/agentic-seek-front/src/App.js
+++ b/frontend/agentic-seek-front/src/App.js
@@ -4,7 +4,8 @@ import axios from 'axios';
import './App.css';
import { colors } from './colors';
-const BACKEND_URL = process.env.BACKEND_PORT || 'http://0.0.0.0:8000';
+const BACKEND_URL = 'http://localhost:7777' || process.env.REACT_APP_BACKEND_URL;
+console.log('Using backend URL:', BACKEND_URL);
function App() {
const [query, setQuery] = useState('');
diff --git a/llm_router/dl_safetensors.sh b/llm_router/dl_safetensors.sh
index 7fd1a51..5937d0d 100755
--- a/llm_router/dl_safetensors.sh
+++ b/llm_router/dl_safetensors.sh
@@ -1,6 +1,6 @@
##########
# Dummy script to download the model
-# Because dowloading with hugging face does not seem to work, maybe I am doing something wrong?
+# Because downloading with hugging face does not seem to work, maybe I am doing something wrong?
# AdaptiveClassifier.from_pretrained("adaptive-classifier/llm-router") ----> result in config.json not found
# Therefore, I put all the files in llm_router and download the model file with this script, If you know a better way please raise an issue
#########
@@ -30,4 +30,4 @@ if [ ! -f "$FILENAME" ]; then
fi
else
echo "File already exists, skipping download"
-fi
\ No newline at end of file
+fi
diff --git a/llm_router/examples.json b/llm_router/examples.json
index 8240354..dde1903 100644
--- a/llm_router/examples.json
+++ b/llm_router/examples.json
@@ -6966,7 +6966,7 @@
0.010188529267907143
],
"label": "LOW",
- "text": "You are AoControl, a helpful and knowledgeable agent. To achieve your goal of answering complex questions correctly, you have access to the following tools:\n AoInnovus: An agent with knowledge of the Cadence Innovus User Guide and corresponding Tcl command usage\n AoTcl: An agent with knowledge of the Tcl language\nTo answer questions, you'll need to go through multiple steps involving step-by-step thinking and selecting appropriate tools and their inputs; tools will respond with observations.\nWhen you are ready for a final answer, respond with the `Final Answer:`\nUse the following format:\nQuestion: The question to be answered\nTHought: Reason if you have the final answer. If yes, anwer the question. If not, find out the missing information needed to answer it.\nTool: Pick one of {AoInnovus, AoTcl}\nTool Input: The input for the tool\nObservation: The tool will respond with the result\n...\nFinal Answer: The final answer to the question, make it short (50-100 words)\nThought, Tool, Tool Input, and Observation steps can be repeated multiple times, but sometimes we can find an answer in the first pass.\n---\nQuestion: How do I identify the impact of metal fill on my timing violations?\nThought: Let's think step-by-step, I first need to"
+ "text": "You are AoControl, a helpful and knowledgeable agent. To achieve your goal of answering complex questions correctly, you have access to the following tools:\n AoInnovus: An agent with knowledge of the Cadence Innovus User Guide and corresponding Tcl command usage\n AoTcl: An agent with knowledge of the Tcl language\nTo answer questions, you'll need to go through multiple steps involving step-by-step thinking and selecting appropriate tools and their inputs; tools will respond with observations.\nWhen you are ready for a final answer, respond with the `Final Answer:`\nUse the following format:\nQuestion: The question to be answered\nTHought: Reason if you have the final answer. If yes, answer the question. If not, find out the missing information needed to answer it.\nTool: Pick one of {AoInnovus, AoTcl}\nTool Input: The input for the tool\nObservation: The tool will respond with the result\n...\nFinal Answer: The final answer to the question, make it short (50-100 words)\nThought, Tool, Tool Input, and Observation steps can be repeated multiple times, but sometimes we can find an answer in the first pass.\n---\nQuestion: How do I identify the impact of metal fill on my timing violations?\nThought: Let's think step-by-step, I first need to"
},
{
"embedding": [
@@ -7743,4 +7743,4 @@
"text": "Generate service startup ideas based on experiences around data science and artificial intelligence for teenagers. For example, when I say \u201cI wish there was an exciting way to explore the worlds of data science and artificial intelligence this summer\u201d, you generate a business plan for the digital startup complete with idea name, a short one liner, target user persona, user\u2019s pain points to solve, main value propositions, sales & marketing channels, revenue stream sources, cost structures, key activities, key resources, key partners, idea validation steps, estimated 1st year cost of operation, and potential business challenges to look for. Write the result in a markdown table."
}
]
-}
\ No newline at end of file
+}
diff --git a/prompts/base/coder_agent.txt b/prompts/base/coder_agent.txt
index 5323190..8baef06 100644
--- a/prompts/base/coder_agent.txt
+++ b/prompts/base/coder_agent.txt
@@ -20,7 +20,7 @@ toto.py
You can execute bash command using the bash tag :
```bash
#!/bin/bash
-ls -la # exemple
+ls -la # example
```
You can execute python using the python tag
@@ -48,5 +48,5 @@ Some rules:
- You do not ever need to use bash to execute code.
- Do not ever tell user how to run it. user know it.
- If using gui, make sure echap or exit button close the program
-- No lazyness, write and rewrite full code every time
-- If query is unclear say REQUEST_CLARIFICATION
\ No newline at end of file
+- No laziness, write and rewrite full code every time
+- If query is unclear say REQUEST_CLARIFICATION
diff --git a/prompts/base/planner_agent.txt b/prompts/base/planner_agent.txt
index a4762d3..fcc3c10 100644
--- a/prompts/base/planner_agent.txt
+++ b/prompts/base/planner_agent.txt
@@ -29,7 +29,7 @@ You: Sure, here is the plan:
## Task 3: I will setup the project using the file agent
-## Task 4: I asign the coding agent to make a weather app in python
+## Task 4: I assign the coding agent to make a weather app in python
```json
{
@@ -74,7 +74,7 @@ Rules:
- Put your plan in a json with the key "plan".
- specify work folder name to all coding or file agents.
- You might use a file agent before code agent to setup a project properly. specify folder name.
-- Give clear, detailled order to each agent and how their task relate to the previous task (if any).
+- Give clear, detailed order to each agent and how their task relate to the previous task (if any).
- The file agent can only conduct one action at the time. successive file agent could be needed.
- Only use web agent for finding necessary informations.
- Always tell the coding agent where to save file.
@@ -82,4 +82,4 @@ Rules:
- Make sure json is within ```json tag
- Coding agent should write the whole code in a single file unless instructed otherwise.
- Do not use python for NLP analysis of a text, you can review a text with the casual agent
-- One step, one agent.
\ No newline at end of file
+- One step, one agent.
diff --git a/sources/agents/planner_agent.py b/sources/agents/planner_agent.py
index a588604..c324da7 100644
--- a/sources/agents/planner_agent.py
+++ b/sources/agents/planner_agent.py
@@ -200,7 +200,7 @@ class PlannerAgent(Agent):
{last_agent_work}
Agent {id} work was a {tool_success_str} according to system interpreter.
{next_task}
- Is the work done for task {id} leading to sucess or failure ? Did an agent fail with a task?
+ Is the work done for task {id} leading to success or failure ? Did an agent fail with a task?
If agent work was good: answer "NO_UPDATE"
If agent work is leading to failure: update the plan.
If a task failed add a task to try again or recover from failure. You might have near identical task twice.
@@ -288,4 +288,4 @@ class PlannerAgent(Agent):
steps = len(agents_tasks)
i += 1
- return answer, ""
\ No newline at end of file
+ return answer, ""
diff --git a/sources/text_to_speech.py b/sources/text_to_speech.py
index 310bfee..993ce28 100644
--- a/sources/text_to_speech.py
+++ b/sources/text_to_speech.py
@@ -114,7 +114,7 @@ class Speech():
def shorten_paragraph(self, sentence):
#TODO find a better way, we would like to have the TTS not be annoying, speak only useful informations
"""
- Find long paragraph like **explaination**: