Version 0.0.53 - both version have lost their key setting, leading to:

Error sending message
Oops! Looks like you missed some required information. Please fill in all the required fields before continuing

This is because Firefox doesn't support -webkit-text-security, which is used in the .password class. You can sidestep it though by using https://github.com/noppa/text-security:

// npm install --save text-security
@import "text-security/text-security.css";

@supports not (-webkit-text-security: disc) {
  .password {
    font-family: text-security-disc;
  }
}

Demo: https://jsfiddle.net/5wg3n7hu/

I can't connect the model to any tool or LLMMathChain. OpenAI model input type is str. (0.0.40 version on windows)

Git cloned and then ran docker compose up in the langflow directory.
Seemed to spin up fine, but I'm getting errors when I go to localhost:3000.
Keep getting proxy error.
Running on linux mint, but that shouldn't cause any issues since it's in docker.
See screenshots.

Need some type of node to use langchainhub components in the flow

I receive this error when putting in a long descriptive description in the new tool widget:
There was an error loading the langchain_object. Please, check all the nodes and try again.

I know the other issue was closed thinking this was fixed but the same error still is happening.
Or is there a different way to run it other than just "langflow" in cli?

Add the type in the internal part of the box and remove this tooltip.

How to reproduce:

• First set up a chain with memory and llm

• then remove the llm

• add a new llm

• get the error
  

Facing error when building image.

Logspace repo on Docker Hub is not accessible.

I got this error ModuleNotFoundError: No module named 'fcntl'

Add documentation in README.md and other if needed demonstrating how to import a langchain agent.

Currently the value key is not created and raises an issue in the backend.

This issue is for us to discuss this topic and its implementation.
This is probably one of the most interesting parts of Langchain and we should build a structure that will allow us to have a more accessible interface with it.

Right now we work with a pretty straight line between LangFlow and langchain but this will require us to point to the run function instead of just building and calling the agent or run function.

I think one approach is to associate the Agent Output node to the action creating a tool from it.
This requires a blank Tool node that has Name, Description, and Func parameters.
The Func could come from outside (Agent Output or Chain output) or we could allow the user to pass a python script that we would have to parse in the backend.

The Agent or Chain output is pretty straightforward in the frontend but will require custom implementation in the backend i.e create the agent and then set its run function to a new Tool.

The python script would require checking for imports and parsing the function itself. There might be solutions for this in the community already.
One option though would be to first allow the use of the requests package for now and build on top of that once we get it working.

The implementation might get confusing once we implement this so the point of this issue is for us to discuss the course of action to build a structure that is robust possibly using pydantic.BaseModel to get the validation basically for free and use an object-oriented approach to build the graph.

If we create classes inheriting from LangChain's classes and we setup functions such as Chain.as_tool(name, description) and maybe a class called GraphProcessor that processes the JSON and goes over the nodes and edges to build the LangChain Agent, I think it will be easier to maintain once LangChain implements a breaking change.

I run docker compose up
logs end up with:

langflow-frontend-1  | ERROR in ./src/App.tsx 16:0-53
langflow-frontend-1  | Module not found: Error: Can't resolve 'react-error-boundary' in '/home/node/app/src'
langflow-frontend-1  | 
langflow-frontend-1  | webpack compiled with 1 error and 1 warning
langflow-frontend-1  | ERROR in src/App.tsx:12:31
langflow-frontend-1  | TS2307: Cannot find module 'react-error-boundary' or its corresponding type declarations.
langflow-frontend-1  |     10 | import { locationContext } from "./contexts/locationContext";
langflow-frontend-1  |     11 | import TabsManagerComponent from "./pages/FlowPage/components/tabsManagerComponent";
langflow-frontend-1  |   > 12 | import { ErrorBoundary } from "react-error-boundary";
langflow-frontend-1  |        |                               ^^^^^^^^^^^^^^^^^^^^^^
langflow-frontend-1  |     13 | import CrashErrorComponent from "./components/CrashErrorComponent";
langflow-frontend-1  |     14 | import { TabsContext } from "./contexts/tabsContext";
langflow-frontend-1  |     15 |

Apparently this broke at some point after 0.0.45

The error currently just tells us there's something missing but it would be very useful if told what is missing.

Discussed in #41

Just installed and dropped HuggingFaceHub into the canvas, it asks for HF token but no way to set the model name. Is this implemented at all?

I've created a localized https://github.com/linonetwo/langchain-alpaca based on langchain-js

Can I use it inside langflow?

I get how to connect the LLM and Prompt, but are there components memory?

Adding SearxNG as a tool as an alternative to SerpAPI and Serper

In Langchain 0.0.54 I receive the message "The template you are attempting to use does not contain any variables for data entry." when I select "Check & Save" on the text entry modal. The text does show up inside of the PromptTemplate block, but when attempting to use the block, I receive the message "Oops! Looks like you missed some required information. Please fill in all the required fields before continuing.

It would be great to have integration with LlamaHub.

Hey there!

Just installed this and playing around with it.
Unfortunately I'm getting this error as soon as I try a basic example

Error: A single string input was passed in, but this chain expects multiple inputs (set()). When a chain expects multiple inputs, please call it by passing in a dictionary, eg `chain({'foo': 1, 'bar': 2})`

Is there something I'm not configuring correctly and I'm missing?

Thanks in advance for this amazing project

Hello!

It would seem that FewShotPromptTemplate expects a dict list which if not placed, will throw this error

How exactly to place a dict list inside a FewShotPromptTemplate?
I have not seen a way to instance a dict list inside the UI

Need to add ZeroShotPrompt inside prompts on the side bar

Couldn't find this anywhere in the UI. Would be nice to have.

Is there a way to import custom LangChain components (tools, chains, agents, etc.)? The current selection is very limited and doesn't seem to keep up with what's already in the core LangChain library.

I am getting an error when using langflow:

Steps to reproduce:

brew install pyenv
pyenv install 3.10.10 # Saw you are using Python 3.10 from Docker file so installed that
pyenv local 3.10.10
pyenv virtualenv 3.10.10 langflow
virtualenv activate langflow
pip install langflow
langflow

I dragged the OpenAI LLM into the screen, copied my API key into the text box for it, and then in the chat field typed 'Hi'.
Upon pressing enter, I get an error in the lower left hand corner saying:
Error: 'OpenAI' object has no attribute 'input_keys'

Here is a screenshot of the error.

Am I not using it right or is this a bug? Happy to contribute to the project as I come up to speed on it more.

1. Langflow worked when I installed it using pip.
2. I wanted to add additional agents from the langchain-hub. So I clicked the import button on the top-right import button and selected the self-ask-with-search/agent.json file.
3. From that point onward, the UI would disappear within milliseconds of loading. IE, when I Ctrl+Shift+R'ed, I would briefly see the origonal UI, but it would be gone by the 0.25 second mark. In the Chrome debugger, I observed this message appear at the time that the UI went blank:

Uncaught TypeError: Cannot read properties of undefined (reading 'map')
    at tp (index.tsx:164:21)
    at Ea (react-dom.production.min.js:167:137)
    at El (react-dom.production.min.js:290:337)
    at xs (react-dom.production.min.js:280:389)
    at ys (react-dom.production.min.js:280:320)
    at gs (react-dom.production.min.js:280:180)
    at as (react-dom.production.min.js:271:88)
    at is (react-dom.production.min.js:268:429)
    at S (scheduler.production.min.js:13:203)
    at MessagePort.P (scheduler.production.min.js:14:128)

By setting a breakpoint in the debugger, I could see the UI correctly rendered prior to the error. After this error happens, the screen is completely white.

4. I tried restarting the langflow server. I tried force reloading. I also tried uninstalling and reinstalling langflow. No change in behavior.

How can I revert my system to its state prior to importing the json file? I don't need recovery, I just need to restart as a fresh user. Thanks!

Implement and test Langchain's ChatOpenAI.

This issue is for us to discuss this topic and its implementation.

Let's discuss langflow in replit and test it so that we can see if it works.

If a node has no inputs at all, there should just be the outputs text.

Or load it with one click.

(venv) PS C:\Users\XXX\PycharmProjects\XXX> langflow
Traceback (most recent call last):
File "C:\Users\XXX\AppData\Local\Programs\Python\Python39\lib\runpy.py", line 197, in _run_module_as_main
return run_code(code, main_globals, None,
File "C:\Users\XXX\AppData\Local\Programs\Python\Python39\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "C:\Users\XXX\PycharmProjects\XXX\venv\Scripts\langflow.exe_main.py", line 4, in
File "C:\Users\XXX\PycharmProjects\XXX\venv\lib\site-packages\langflow_backend_init.py", line 1, in
from langflow_backend.interface.loading import load_flow_from_json # noqa
File "C:\Users\XXX\PycharmProjects\XXX\venv\lib\site-packages\langflow_backend\interface\loading.py", line 4, in
from langchain.agents.loading import load_agent_executor_from_config
ImportError: cannot import name 'load_agent_executor_from_config' from 'langchain.agents.loading' (C:\Users\XXX\PycharmProjects\XXX\venv\lib\site-packages\langchain\agents\loading.py)
(venv) PS C:\Users\XXX\PycharmProjects\XXX>

Hey LangFlow Dev Team!

I have a feature request that I think would be awesome for the platform. Can you add a local server with Docker, so users can use chained prompts on local networks? It's like an OpenAI API server proxy, and would let us experiment with more complex flows for personal servers and systems.

Hey nice work in Dev, just noticed that the format instructions option isnt available on zero shot prompt, can you ensure it is added?
Thanks,
ionstorm

I've installed langflow via pip on my Mac and ran it using langflow. But it seems to be stuck. I get the following when CTRL-Cing out of the process.

Traceback (most recent call last):
  File "/usr/local/bin/langflow", line 5, in <module>
    from langflow.__main__ import main
  File "/usr/local/lib/python3.11/site-packages/langflow/__init__.py", line 1, in <module>
    from langflow.interface.loading import load_flow_from_json  # noqa
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/langflow/interface/loading.py", line 3, in <module>
    from langflow.interface.types import get_type_list
  File "/usr/local/lib/python3.11/site-packages/langflow/interface/types.py", line 1, in <module>
    from langflow.interface.listing import list_type
  File "/usr/local/lib/python3.11/site-packages/langflow/interface/listing.py", line 1, in <module>
    from langchain import chains, agents, prompts
  File "/usr/local/lib/python3.11/site-packages/langchain/__init__.py", line 57, in <module>
    set_default_callback_manager()
  File "/usr/local/lib/python3.11/site-packages/langchain/callbacks/__init__.py", line 31, in set_default_callback_manager
    set_tracing_callback_manager(session)
  File "/usr/local/lib/python3.11/site-packages/langchain/callbacks/__init__.py", line 45, in set_tracing_callback_manager
    handler.load_default_session()
  File "/usr/local/lib/python3.11/site-packages/langchain/callbacks/tracers/langchain.py", line 83, in load_default_session
    r = requests.get(
        ^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 73, in get
    return request("get", url, params=params, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 59, in request
    return session.request(method=method, url=url, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 587, in request
    resp = self.send(prep, **send_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 701, in send
    r = adapter.send(request, **kwargs)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 489, in send
    resp = conn.urlopen(
           ^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 703, in urlopen
    httplib_response = self._make_request(
                       ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 449, in _make_request
    six.raise_from(e, None)
  File "<string>", line 3, in raise_from
  File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 444, in _make_request
    httplib_response = conn.getresponse()
                       ^^^^^^^^^^^^^^^^^^
  File "/usr/local/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py", line 1374, in getresponse
    response.begin()
  File "/usr/local/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py", line 318, in begin
    version, status, reason = self._read_status()
                              ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py", line 279, in _read_status
    line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/Cellar/[email protected]/3.11.2_1/Frameworks/Python.framework/Versions/3.11/lib/python3.11/socket.py", line 706, in readinto
    return self._sock.recv_into(b)
           ^^^^^^^^^^^^^^^^^^^^^^^

File "py390/lib/python3.9/site-packages/langflow/utils/logger.py", line 4, in
from rich.logging import RichHandler
ModuleNotFoundError: No module named 'rich'

After pip install rich all was good

Awesome release by the way!

langflow % docker-compose up -d
[+] Building 36.9s (27/27) FINISHED
=> [langflow-backend internal] load build definition from dev.Dockerfile 0.0s
=> => transferring dockerfile: 603B 0.0s
=> [langflow-frontend internal] load build definition from dev.Dockerfile 0.0s
=> => transferring dockerfile: 553B 0.0s
=> [langflow-backend internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [langflow-frontend internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [langflow-backend internal] load metadata for docker.io/library/python:3.10-slim 1.9s
=> [langflow-frontend internal] load metadata for docker.io/library/node:19-bullseye-slim 2.0s
=> [langflow-backend 1/7] FROM docker.io/library/python:3.10-slim@sha256:7b0a5cefbcdd085faa21533c21549e55a7e66f5aed40f8d1f4de13a017e352cd 6.2s
=> => resolve docker.io/library/python:3.10-slim@sha256:7b0a5cefbcdd085faa21533c21549e55a7e66f5aed40f8d1f4de13a017e352cd 0.0s
=> => sha256:93a67280259393dc61b3b00d448dfe8c71e2fa81bfd4242f464ee813460608c7 1.06MB / 1.06MB 1.1s
=> => sha256:8dcaf4f41922b5c226f133fe4fc15c680a48807ebf35153a0dc3dabf51ee2203 11.62MB / 11.62MB 1.0s
=> => sha256:7b0a5cefbcdd085faa21533c21549e55a7e66f5aed40f8d1f4de13a017e352cd 1.65kB / 1.65kB 0.0s
=> => sha256:8d388bd2c07d176d5a9dded8fc8f5a10514f26323042c9bc02bd610cae3b494f 1.37kB / 1.37kB 0.0s
=> => sha256:35ce97c3e6679fbc15551848fae67b75cdc8b304c7b2ddba5196bddf7af5f54a 6.91kB / 6.91kB 0.0s
=> => sha256:fcdb9667c46b09d1c1d058681ea4a1db41e66bbc1a71d873a0c9da4f7a92947d 30.06MB / 30.06MB 5.1s
=> => sha256:3fdc970d6941574ded95783f1ffef19e8f4910579cd43c2777b762a31785cf96 244B / 244B 1.2s
=> => sha256:5e42bc20b98e6386bb4dd78946b51c72241099523dfe261d4a05142f54b0dd92 3.37MB / 3.37MB 2.1s
=> => extracting sha256:fcdb9667c46b09d1c1d058681ea4a1db41e66bbc1a71d873a0c9da4f7a92947d 0.5s
=> => extracting sha256:93a67280259393dc61b3b00d448dfe8c71e2fa81bfd4242f464ee813460608c7 0.1s
=> => extracting sha256:8dcaf4f41922b5c226f133fe4fc15c680a48807ebf35153a0dc3dabf51ee2203 0.2s
=> => extracting sha256:3fdc970d6941574ded95783f1ffef19e8f4910579cd43c2777b762a31785cf96 0.0s
=> => extracting sha256:5e42bc20b98e6386bb4dd78946b51c72241099523dfe261d4a05142f54b0dd92 0.1s
=> [langflow-backend internal] load build context 0.1s
=> => transferring context: 10.09MB 0.1s
=> [langflow-frontend base 1/5] FROM docker.io/library/node:19-bullseye-slim@sha256:8ac2083552bb3d92abbbda6baaf9b89b054bfa2cde863d965df9c28ac9baef41 6.7s
=> => resolve docker.io/library/node:19-bullseye-slim@sha256:8ac2083552bb3d92abbbda6baaf9b89b054bfa2cde863d965df9c28ac9baef41 0.0s
=> => sha256:0835210398882ef429d081ed531af92a36ccee0aa45c2060af9166875b637e5a 6.86kB / 6.86kB 0.0s
=> => sha256:fcdb9667c46b09d1c1d058681ea4a1db41e66bbc1a71d873a0c9da4f7a92947d 30.06MB / 30.06MB 5.0s
=> => sha256:8ac2083552bb3d92abbbda6baaf9b89b054bfa2cde863d965df9c28ac9baef41 1.21kB / 1.21kB 0.0s
=> => sha256:be8c55668e437bf00e125597b9449680a75c7190dc829b6401f94c1ef9570129 1.37kB / 1.37kB 0.0s
=> => sha256:12208f06d5953722cdff5ac0cdba75c6b4d1ac5f812cb0b8a3dda599ed15b832 4.19kB / 4.19kB 1.3s
=> => sha256:c57bccfe4039ad5b3a465c56da4cea658d141a49548a2b6c94fa338cb6a020ae 46.77MB / 46.77MB 5.4s
=> => sha256:f990dd30467d49c03ddce76f191e85ed9499edb33a32baa0a1be0fd6924e6d29 2.76MB / 2.76MB 3.2s
=> => sha256:1a49604e8d632e8cc7877f17bae6130bd3e1bb76bc45ce5be709157d92cba4b7 449B / 449B 3.5s
=> => extracting sha256:fcdb9667c46b09d1c1d058681ea4a1db41e66bbc1a71d873a0c9da4f7a92947d 0.5s
=> => extracting sha256:12208f06d5953722cdff5ac0cdba75c6b4d1ac5f812cb0b8a3dda599ed15b832 0.0s
=> => extracting sha256:c57bccfe4039ad5b3a465c56da4cea658d141a49548a2b6c94fa338cb6a020ae 0.9s
=> => extracting sha256:f990dd30467d49c03ddce76f191e85ed9499edb33a32baa0a1be0fd6924e6d29 0.1s
=> => extracting sha256:1a49604e8d632e8cc7877f17bae6130bd3e1bb76bc45ce5be709157d92cba4b7 0.0s
=> [langflow-frontend internal] load build context 0.0s
=> => transferring context: 955.15kB 0.0s
=> [langflow-backend 2/7] WORKDIR /app 0.3s
=> [langflow-backend 3/7] RUN apt-get update && apt-get install gcc curl -y 11.3s
=> [langflow-frontend base 2/5] RUN mkdir -p /home/node/app 0.2s
=> [langflow-frontend base 3/5] RUN chown -R node:node /home/node && chmod -R 770 /home/node 0.3s
=> [langflow-frontend base 4/5] RUN apt-get update && apt-get install -y jq 2.8s
=> [langflow-frontend base 5/5] WORKDIR /home/node/app 0.0s
=> [langflow-frontend builder-client 1/6] RUN echo "BACKEND_URL: http://backend:7860" 0.3s
=> [langflow-frontend builder-client 2/6] WORKDIR /home/node/app 0.0s
=> [langflow-frontend builder-client 3/6] COPY --chown=node:node . ./ 0.0s
=> [langflow-frontend builder-client 4/6] COPY ./set_proxy.sh . 0.0s
=> [langflow-frontend builder-client 5/6] RUN chmod +x set_proxy.sh && ./set_proxy.sh 0.2s
=> [langflow-frontend builder-client 6/6] RUN npm install --loglevel warn 12.7s
=> [langflow-backend 4/7] RUN curl -sSL https://install.python-poetry.org | python3 - 10.8s
=> [langflow-frontend] exporting to image 2.6s
=> => exporting layers 2.6s
=> => writing image sha256:827a866d6afa3b1b1f68c2f6564e871ba6cf1054d875a008fa68830ba57e58f3 0.0s
=> => naming to docker.io/library/langflow-frontend 0.0s
=> [langflow-backend 5/7] COPY poetry.lock pyproject.toml ./ 0.0s
=> [langflow-backend 6/7] COPY ./ ./ 0.0s
=> ERROR [langflow-backend 7/7] RUN poetry config virtualenvs.create false && poetry install --no-interaction --no-ansi 6.2s

[langflow-backend 7/7] RUN poetry config virtualenvs.create false && poetry install --no-interaction --no-ansi:
#0 0.694 Skipping virtualenv creation, as specified in config file.
#0 0.997 Installing dependencies from lock file
#0 1.278
#0 1.278 Package operations: 88 installs, 1 update, 0 removals
#0 1.278
#0 1.279 • Installing packaging (23.0)
#0 1.279 • Installing pyasn1 (0.4.8)
#0 1.279 • Installing six (1.16.0)
#0 1.527 • Installing asttokens (2.2.1)
#0 1.527 • Installing cachetools (5.3.0)
#0 1.528 • Installing certifi (2022.12.7)
#0 1.529 • Installing executing (1.2.0)
#0 1.530 • Installing charset-normalizer (3.1.0)
#0 1.531 • Installing frozenlist (1.3.3)
#0 1.531 • Installing idna (3.4)
#0 1.533 • Installing marshmallow (3.19.0)
#0 1.565 • Installing multidict (6.0.4)
#0 1.571 • Installing mypy-extensions (1.0.0)
#0 1.621 • Installing parso (0.8.3)
#0 1.625 • Installing platformdirs (3.1.1)
#0 1.637 • Installing protobuf (4.22.1)
#0 1.667 • Installing ptyprocess (0.7.0)
#0 1.689 • Installing pure-eval (0.2.2)
#0 1.703 • Installing pyasn1-modules (0.2.8)
#0 1.710 • Installing pyparsing (3.0.9)
#0 1.717 • Installing rsa (4.9)
#0 1.746 • Installing sniffio (1.3.0)
#0 1.752 • Installing traitlets (5.9.0)
#0 1.764 • Installing typing-extensions (4.5.0)
#0 1.768 • Installing urllib3 (1.26.15)
#0 1.788 • Installing wcwidth (0.2.6)
#0 1.911 • Installing aiosignal (1.3.1)
#0 1.912 • Installing anyio (3.6.2)
#0 1.912 • Installing async-timeout (4.0.2)
#0 1.913 • Installing attrs (22.2.0)
#0 1.914 • Installing backcall (0.2.0)
#0 1.915 • Installing decorator (5.1.1)
#0 1.915 • Installing google-auth (2.16.2)
#0 1.916 • Installing googleapis-common-protos (1.58.0)
#0 1.948 • Installing greenlet (2.0.2)
#0 1.965 • Installing httplib2 (0.21.0)
#0 1.969 • Installing jedi (0.18.2)
#0 1.992 • Installing jupyter-core (5.3.0)
#0 2.048 • Installing marshmallow-enum (1.5.1)
#0 2.092 • Installing matplotlib-inline (0.1.6)
#0 2.170 • Installing pexpect (4.8.0)
#0 2.178 • Installing pickleshare (0.7.5)
#0 2.182 • Installing prompt-toolkit (3.0.38)
#0 2.184 • Installing pygments (2.14.0)
#0 2.234 • Installing python-dateutil (2.8.2)
#0 2.265 • Installing pyzmq (25.0.1)
#0 2.286 • Installing requests (2.28.2)
#0 2.289 • Installing stack-data (0.6.2)
#0 2.304 • Installing tornado (6.2)
#0 2.434 • Installing typing-inspect (0.8.0)
#0 2.447 • Installing yarl (1.8.2)
#0 2.948 • Installing aiohttp (3.8.4)
#0 2.949 • Installing click (8.1.3)
#0 2.949 • Installing comm (0.1.2)
#0 2.950 • Installing dataclasses-json (0.5.7)
#0 2.951 • Installing debugpy (1.6.6)
#0 2.952 • Installing google-auth-httplib2 (0.1.0)
#0 2.952 • Installing h11 (0.14.0)
#0 2.953 • Installing google-api-core (2.11.0)
#0 3.002 • Installing ipython (8.11.0)
#0 3.030 • Installing jupyter-client (8.0.3)
#0 3.035 • Installing nest-asyncio (1.5.6)
#0 3.045 • Installing numpy (1.24.2)
#0 3.136 • Installing pathspec (0.11.1)
#0 3.181 • Installing psutil (5.9.4)
#0 3.183 • Installing pydantic (1.10.6)
#0 3.304 • Installing pyyaml (6.0)
#0 3.453 • Updating setuptools (65.5.1 -> 67.6.0)
#0 3.492 • Installing soupsieve (2.4)
#0 3.556 • Installing sqlalchemy (1.4.47)
#0 3.576 • Installing starlette (0.25.0)
#0 3.701 • Installing tenacity (8.2.2)
#0 3.752 • Installing tomli (2.0.1)
#0 3.831 • Installing tqdm (4.65.0)
#0 3.843 • Installing uritemplate (4.1.1)
#0 3.955
#0 3.955 _WheelFileValidationError
#0 3.955
#0 3.955 ["In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_cython.cp39-win_amd64.pyd didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/_pydevd_frame_eval/pydevd_frame_evaluator.cp39-win_amd64.pyd didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/attach_amd64.dll didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/attach_x86.dll didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/inject_dll_amd64.exe didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/inject_dll_x86.exe didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/run_code_on_dllmain_amd64.dll didn't match RECORD", "In /root/.cache/pypoetry/artifacts/f2/96/74/9c8a5447a1d805edc0c82f964602703c805d10cae4b7b14e5d5d546ff0/debugpy-1.6.6-py2.py3-none-any.whl, hash / size of debugpy/_vendored/pydevd/pydevd_attach_to_process/run_code_on_dllmain_x86.dll didn't match RECORD"]
#0 3.955
#0 3.955 at ~/.local/share/pypoetry/venv/lib/python3.10/site-packages/installer/sources.py:289 in validate_record
#0 3.961 285│ f"In {self._zipfile.filename}, hash / size of {item.filename} didn't match RECORD"
#0 3.961 286│ )
#0 3.961 287│
#0 3.961 288│ if issues:
#0 3.961 → 289│ raise _WheelFileValidationError(issues)
#0 3.961 290│
#0 3.961 291│ def get_contents(self) -> Iterator[WheelContentElement]:
#0 3.961 292│ """Sequential access to all contents of the wheel (including dist-info files).
#0 3.961 293│
#0 3.961

failed to solve: executor failed running [/bin/sh -c poetry config virtualenvs.create false && poetry install --no-interaction --no-ansi]: exit code: 1

Adding support for database API such as Pinecone, Weaviate or other vector databases

I would like to have one chain produce some text, and another chain refine that text.

The AzureOpenAI LLM is functionally identical to the OpenAI LLM but requires different parameters.

Azure OpenAI

It would be great to be able to use this configuration!

The backend URL string is currently inferred from port and host and set dynamically at startup. This breaks server deployments in docker containers because the frontend uses a different url than what's exposed to the backend via Docker because of reverse proxies.

Chrome gives the following error<your langflow deployment domain> was loaded over HTTPS, but requested an insecure XMLHttpRequest endpoint 'http://0.0.0.0:8080/all'. This request has been blocked; the content must be served over HTTPS.

It would be great if the documentation included a few minimal working examples to get started with.

For example, it wasn't intuitive to me how to recreate something similar to the ChatGPT web interface.

Improve API and front-end to send chat history to be processed

Hi!

I can install via pip, but cannot run python -m langflow

Pip output:

Requirement already satisfied: langflow in /Users/anishthite/miniconda3/lib/python3.9/site-packages (0.0.32)

python -m langflow output:

/Users/anishthite/miniconda3/bin/python: No module named langflow

Backend should check for necessary environment variables and set them up on the nodes that require them.

Probably a better way would simply acknowledge that the keys are present and use them when the chat request arrives.