2,003 questions
0
votes
0
answers
38
views
I am stuck at this error - Error Loading the Langachain pipeline 'field set'
I am stuck at this error - Error Loading the Langachain pipeline 'field set'.
How can i resolve this error?
Below i have mention my code ,
import os
from langchain_community.vectorstores import FAISS
...
Advice
4
votes
3
replies
62
views
Improve the RAG chatbot result
I am building a local RAG chatbot using LangChain and ChromaDB (PersistentClient). I’m encountering 'hallucinations' when the similarity search returns documents with a low relevance score. How can I ...
- 1
-5
votes
1
answer
95
views
Problem with setting up Langchain agents to use Playwright
I can't make this work:
from langchain_community.agent_toolkits import PlayWrightBrowserToolkit
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent
import asyncio
import ...
1
vote
0
answers
49
views
Agentic RAG tool_calling issue: Groq + LangChain agent fails with tool_use_failed when calling custom tool (Llama 3.3)
I'm building a Streamlit app using LangChain (latest), LangGraph, and Groq with the model:
llama-3.3-70b-versatile
I'm using the modern create_agent() API (LangGraph-backed). The agent has two tools:
...
-7
votes
1
answer
103
views
How to make an AI chatbot respond in Hinglish (Hindi + English mix)? [closed]
I am building a stock assistant chatbot using an LLM.
I want the chatbot to always respond in Hinglish, i.e. a mix of Hindi and English written in Roman script, for example: Aaj market thoda volatile ...
-3
votes
0
answers
39
views
Why is langchain's AsyncHtmlLoader not working but WebBaseLoader is working?
I have the following code. The first data loading call gives error, the second works fine.
url="https://en.wikipedia.org/wiki/2023_Cricket_World_Cup"
from langchain_community....
- 4,567
2
votes
0
answers
23
views
Langgraph Studio Multi-Agent Example: Hierarchical Agents?
I've been using Langchain and Langgraph for some time now and have gained experience working with various multi-agent models, including hierarchical agents and collaboration agents. Recently, I came ...
- 21
3
votes
1
answer
134
views
Langchain dependencies conflict
I'm trying to install and import different elements from Langchain but i keep having an issue with the dependencies. I will paste (1) the tools that i want to use, (2) my current requirements.txt, (3) ...
- 31
Advice
1
vote
3
replies
51
views
Overriding the agent state in Langgraph
I am trying to override the Langgraph's state["messages"] before it reaches the agent, but not sure if I am doing it right. I need to remove some messages from state before sending it to ...
- 3
1
vote
1
answer
123
views
Why does PyMilvus still report “milvus-lite is required” after installing pymilvus[milvus-lite] on Python 3.11?
I’m trying to use Milvus Lite with Python 3.11.9 in a local project that integrates LangChain and Ollama, but I’m unable to get Milvus to run correctly.
Here is my setup:
Python version: 3.11.9
...
- 41
0
votes
0
answers
129
views
Update state messages list before interrup
I'm using Langgraph version 1.2.7 to build a workflow composed of several nodes. Many of these nodes may interrupt the flow by asking the user for clarifications or additional information. The user ...
- 103
1
vote
1
answer
871
views
ImportError: cannot import name 'create_tool_calling_agent' from 'langchain.agents' [duplicate]
from langchain.agents import create_tool_calling_agent
from langchain.agents.agent_executor import AgentExecutor
executor = AgentExecutor(
agent=supervisor_agent,
tools=[insurance_subagent, ...
Advice
0
votes
0
replies
24
views
Using Langchain's MarkdownTextSplitter with a tokenizer
I'm not sure how to chunk a Markdown file with Langchain's MarkdownTextSplitter and at the same making sure the chunks don't overflow the maximum token size for the llm we will be using. As far as I ...
- 579
0
votes
0
answers
97
views
LangGraph seems to ignore tool outputs with Gemini models
I’m experiencing an issue where the LLM correctly invokes a tool (tool call is successful), but it appears unable to interpret or process the tool’s result.
Here is the code to reproduce the issue:
...
- 131
1
vote
0
answers
122
views
Cannot response as stream token-by-token when an agent is a part of a workflow in Langgraph
I am designing a complex workflow in Langgraph where there will be multiple agents. Some of the agents will be intermediary and some other will be user-facing (that is I will show the output of those ...
- 2,984