Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update termination logic to fix #117 #155

Merged
merged 4 commits into from
Oct 9, 2023
Merged

Update termination logic to fix #117 #155

merged 4 commits into from
Oct 9, 2023

Conversation

thinkall
Copy link
Collaborator

@thinkall thinkall commented Oct 8, 2023

Why are these changes needed?

Address #117 RAG-agent max_consecutive_auto_reply doesn't work as expected

The issue is caused by that once update_context is activated, the default check_termination_and_human_reply will not be executed. In this PR, check_termination_and_human_reply is moved to run before _generate_retrieve_user_reply, and _is_termination_msg_retrievechat is updated accordingly so that termination can be correctly detected based on the task and the message.

Related issue number

Closes #117

Checks

@codecov-commenter
Copy link

codecov-commenter commented Oct 8, 2023

Codecov Report

Merging #155 (aed65da) into main (19f8711) will decrease coverage by 0.14%.
Report is 1 commits behind head on main.
The diff coverage is 0.00%.

@@            Coverage Diff             @@
##             main     #155      +/-   ##
==========================================
- Coverage   41.31%   41.17%   -0.14%     
==========================================
  Files          17       17              
  Lines        2084     2091       +7     
  Branches      466      467       +1     
==========================================
  Hits          861      861              
- Misses       1147     1154       +7     
  Partials       76       76              
Flag Coverage Δ
unittests 41.08% <0.00%> (-0.14%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files Coverage Δ
...gen/agentchat/contrib/retrieve_user_proxy_agent.py 4.23% <0.00%> (-0.17%) ⬇️

Copy link
Contributor

@sonichi sonichi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@thinkall thinkall added this pull request to the merge queue Oct 9, 2023
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to no response for status checks Oct 9, 2023
@thinkall thinkall enabled auto-merge October 9, 2023 01:52
@thinkall thinkall added this pull request to the merge queue Oct 9, 2023
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to no response for status checks Oct 9, 2023
@thinkall thinkall enabled auto-merge October 9, 2023 03:42
@thinkall thinkall added this pull request to the merge queue Oct 9, 2023
Merged via the queue into main with commit 95e4c58 Oct 9, 2023
16 of 19 checks passed
@thinkall thinkall deleted the rag_groupchat branch October 9, 2023 04:22
@wiiiktor
Copy link

wiiiktor commented Oct 9, 2023

I no longer have error "maximum recursion depth exceeded while calling a Python object", but now agent returns two answers (both of them are ok, but why two? is this a normal behaviour?). Example answer looks like below. In the meantime, agent get more snippets, which is ok, but I expected agent to write something like "I need more knowledge".


assistant (to ragproxyagent):

Dear Toan,
We can definitely provide you with a 38T Chainring GTRO gearbox. As for the ERider 73mm torque sensing bottom bracket compatibility, we have a solution for 73mm shells as well. When making a purchase, please specify "BB73mm" in the comment. As for the prices, you will have to check our website for the current prices as they may vary. Please, let me know if you have any other questions.

@wiiiktor
Copy link

wiiiktor commented Oct 9, 2023

This is the full outuput:

'''
/Users/wiiiktor/Documents/code/autogen3/.venv/bin/python /Users/wiiiktor/Documents/code/autogen3/notebook/rag-maile.py
['Hello Wiktor, I wanted to get a price on your 38t Chainring GTRO with an ERider 73mm torque sensing bottom bracket. I will be using it on my ebike converted MTB. Thanks in advance for your time. Best Regards, Toan']
['Our gearbox is not compatible with this BB torque sensor, sorry...']

Below are outputs of Case 1 <<<<<<<<<<<<

Trying to create collection.
Collection autogen-docs already exists.
doc_ids: [['doc_37', 'doc_23', 'doc_35', 'doc_20', 'doc_60']]
Adding doc_id doc_37 to context.
Adding doc_id doc_23 to context.
Adding doc_id doc_35 to context.
Adding doc_id doc_20 to context.
Adding doc_id doc_60 to context.
ragproxyagent (to assistant):

You're a retrieve augmented chatbot.
You answer user's questions based on your own knowledge
and the context provided by the user. You must think step-by-step.

First, please learn the following examples of question-answer pairs.

QUESTION: I have a Merkava FatFold 500 folding bike with a BB shell 100mm and 1.37x24 threaded cup (L & R).
The sensor slips on the shell shaft and lock into the cup teeth. From what I can see, everything looks compatible
with the GTRO but I just want to be certain.I am also not certain I have much space on the left handle for the shifter,
maybe the Twist-Grip would be a better fitment.So GTRO for Ebike or for folding?Thank you!

ANSWER: Dear Stephane, yes, it all looks compatible, we even sometimes purchase Bottom Brackets from the same company
(Gineyea); there should be no problems with PAS; we can send you both trigger and grip shifter,
but one of them would be used (with just a few minor scratches), so that you can change shifter
if you have no space on the handle bar; folding process of this bike is not creating any conflict with the gearbox;
in case of any other questions let me know!

QUESTION: Hello Efneo. Really interesting product.

  1. Are the chainrings on the 28T replaceable? (which BCD)
  2. What is the weight of the efneo crankset? (please specify if this weight include BottomBracket)

ANSWER: Dear Steffen, in reply to your questions:

  1. Are the chainrings on the 28T replaceable? (which BCD?)

we can offer you a version with 28T chainring OR 130mm BCD adapter, but you need to make a decision in advance; however, if you purchase the 28T version, we can offer you a 37T chainring to be installed on top - please, see this manual: http://efneo.com/filesss/manuals/external-chainring-attachment.pdf
In terms of durability, our 28T chainring is made from chromoly steel 30 HRC, which is much above the standard derailleur chainring, so it simply will never wear in practice (we have clients who covered 15 000 miles, and topic of chainring wearing out did not come up)

  1. What is the weight of the efneo crankset? (please specify if this weight include BottomBracket)

the gearbox weighs 1200g (without bottom bracket, left crank and shifter)

QUESTION: Hello again, Can one of your cranksets be used with Alfine 11?
With a Gates belt?
With a T47 BB?
Can it be used with Di2 shifters?
Stan, Yours.

ANSWER: Dear Stan, my answers below:
Can one of your cranksets be used with Alfine 11? -> Yes
With a Gates belt? -> Yes
With a T47 BB? -> Yes, but you need to use this adapter:
https://candncycles.co.uk/product/8498068/fsa-t47-to-bsa-68-73-83mm-bottom-bracket-adapter-el316/option/
Can it be used with Di2 shifters? -> Yes

QUESTION: I am trying to install one of your systems to a Strida. The drive side crank doesn't seem
to be going on far enough. The official instructions say that I need 30.5mm of axle but mine is measuring 28mm.
Where should I go from here? Taylor.

ANSWER: Dear Taylor,
28mm is ok, please, see the drawing:
http://efneo.com/filesss/manuals/BB-68mm-dim.png
(30.5mm is when you measure together with the BB cup flange)
If you have any other questions, let me know!

Second, please answer the question below by thinking step-by-step.
You can ask for appropriate QUESTION-ANSWER examples as your context, if you consider them helpful.

Context QUESTION-ANSWER examples: {"question": "Hello! I'm hoping you might be able to assist me with a few questions I have about your GTRO in relation with my trike. I have a 2016 AZUB TRIcon 20" trike. I currently have a SRAM DD3 IGH, paired with a nine cog Shimano HG cassette and a single 45T Shimano Alfine 150mm crank. I'm finding myself running out of speed in high gear, e.g. I can't seem to get above 16-18mph going flat in my high gear. I'm curious to find out if the 38T version of your GTRO would allow me a higher top-end speed or would I consider purchasing the adapter unit with a 52T cog, for example? Additionally, would you please tell me which bottom bracket size is compatible with my AZUB trike? Finally, I noticed a $100 off coupon flashed on my screen when I visited your site a bit ago today. Would you please share that coupon code as I missed writing it down? Thanks much, in advance, for any insight you can provide! Regards, Kory", "answer": "Dear Kory, please, see my replies to the points you raised: ...38T version or adapter with 52T? >> our 38T version comes with the adapter (130mm-BCD standard), so you can try the 38T first, >> but if you wish to migrate to 52T, you can do it at any time; >> the 38T chainring will give you "gears" equivalent to 38T-54T-68T which bottom bracket size is compatible with my AZUB trike? >> 68mm-wide (by the way, we tested our gearbox with AZUB) $100 off coupon >> sure, here it is: GTRO100"}
{"question": "Hi, I have a Prioirty Continuum Onyx bike which has a NuVinci/Enviolo N330 hub and Gates s100 Beltdrive Crankset with 50T front CDN chainring and 24T CDX rear cog with a CDN belt. Would the GTRO Efneo drive work with my bike? I think it should. I am not concerned about the bottom bracket requirements of 68 mm and English thread but rather about the front cog and how well to install it. The Gates manual doesn’t approve a 28T front cog with a 24T rear cog. So I am not sure how your drive could possibly work in my bike. However, one of the bike owners in your website testimonials also has a NuVinci hub but uses a bike chain instead of Gates belt so I thought perhaps there is hope for me. Anyway, I just wanted to ask your opinion before I placed an order for it with you. I am willing to pay extra for a customized solution from you.", "answer": "Dear Nolin, the photos that you can see at our website show a Gates front beltring with 46 teeth (28 teeth chainring is used for a standard chain, so this is a different world ;) ). We offer a gearbox with a 5-bolt adapter, at 130mm BCD (5 bolts are included into our product). You can use this beltring with our adapter; we do not sell Gates components: https://www.amazon.com/Gates-Carbon-Drive-CenterTrack-Pulley/dp/B00FUS1MTA. You would probably need to purchase a new belt, probably 22 mm shorter, if I count it correctly. If you have any other questions, please, let me know."}
{"question": "Hallo Wiktor, I have a bike with a 73mm bottom bracket. Do you have an Efneo gearbox that will fit this bike? Thanks, Seon Caimbeul", "answer": "Dear Seon, please write "BB73mm" in the comment, when making a purchase; we will need few days more for making the shipment, but 73mm is available."}
{"question": "Compatibility? Terra Trike Rover, I8 (internal 8 gear rear hub Sturmey Archer ), 32 tooth front ring.", "answer": "Dear Macwildstar, 1// in fact, our gearbox offers three 28T-40T-50T chainrings (the 28T is physical and 40T-50T are vertical), so you may probably want to compare your current 32T with our middle virtual chainring of 40T. If you enlarge your rear sprocket by 25%, you will keep the same ratio with our middle chairing (40T) with the rear sprocket, as you currently have; I see at Sturmey Archer website that they offer rear sprockets with 20, 23 or 25 teeth - what do you have atm?.. BUT, you do not necessarily need to match your current frontrear ratio; simply, we encourage you to first try our gearbox with your original rear sprocket and make a decision based on your experience 2// our gearbox is compatible with rear gearboxes, but you should probably check the Sturmey Archer manual, too 3// our gearbox works with the most typical BB shell, having BSA / ISO / English thread, but I see on photos, that https://www.terratrike.com/shop/rover-i8/ almost for sure uses it; anyway, you may confirm it with terratrike.com or with some bike mechanic 4// however, we are waiting for another batch of gearboxes to come, our current stock is empty; we will send you an email, when we open sales again; sorry for the inconvenience -- Regards, Wiktor Migaszewski +48 692 361 761 -- http://www.efneo.com http://www.efneo.com/patents Efneo Sp. z o.o., KRS 0000492928, Kapitał zakładowy 318 920,00 zł niedz., 16 cze 2019 o 21:25 Efneo napisał(a): > Sent from: [email protected] > Message: Compatibility? Terra Trike Rover, I8 (internal 8 gear rear hub Sturmey Archer ), 32 tooth front ring."}
{"question": "Can the efneo be used with a torque sensing bottom bracket? If so, is there one you can recommend for a 73mm bb shell? Thank you!", "answer": "Dear Mathis, I should have a 73mm version of the Sempu T2.3 sensor: http://efneo.com/filesss/manuals/sempu-documentation.pdf Let me check and get back to you."}

QUESTION: Hello Wiktor, I wanted to get a price on your 38t Chainring GTRO with an ERider 73mm torque sensing bottom bracket. I will be using it on my ebike converted MTB. Thanks in advance for your time. Best Regards, Toan
A:


huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using tokenizers before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using tokenizers before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
assistant (to ragproxyagent):

Dear Toan,

To provide you with the price, I would kindly ask you to check our webpage as it has all the detailed prices and even promotions available. As for the 73mm Sempu T2.3 torque sensing bottom bracket compatibility, our GTRO is compatible with it. Hence, it should be perfectly suitable for your e-bike converted MTB.

If you decide to purchase the GTRO, please make sure to write "BB73mm" and "Sempu T2.3 sensor" in the comments section during purchase. Just a reminder that the delivery might take a bit longer for this specific customization.

In case there're any other queries or specifications needed, feel free to reach out.

Best, Wiktor


Updating context and resetting conversation.
doc_ids: [['doc_45', 'doc_21', 'doc_33', 'doc_25', 'doc_51']]
Adding doc_id doc_45 to context.
Adding doc_id doc_21 to context.
Adding doc_id doc_33 to context.
Adding doc_id doc_25 to context.
Adding doc_id doc_51 to context.
ragproxyagent (to assistant):

You're a retrieve augmented chatbot.
You answer user's questions based on your own knowledge
and the context provided by the user. You must think step-by-step.

First, please learn the following examples of question-answer pairs.

QUESTION: I have a Merkava FatFold 500 folding bike with a BB shell 100mm and 1.37x24 threaded cup (L & R).
The sensor slips on the shell shaft and lock into the cup teeth. From what I can see, everything looks compatible
with the GTRO but I just want to be certain.I am also not certain I have much space on the left handle for the shifter,
maybe the Twist-Grip would be a better fitment.So GTRO for Ebike or for folding?Thank you!

ANSWER: Dear Stephane, yes, it all looks compatible, we even sometimes purchase Bottom Brackets from the same company
(Gineyea); there should be no problems with PAS; we can send you both trigger and grip shifter,
but one of them would be used (with just a few minor scratches), so that you can change shifter
if you have no space on the handle bar; folding process of this bike is not creating any conflict with the gearbox;
in case of any other questions let me know!

QUESTION: Hello Efneo. Really interesting product.

  1. Are the chainrings on the 28T replaceable? (which BCD)
  2. What is the weight of the efneo crankset? (please specify if this weight include BottomBracket)

ANSWER: Dear Steffen, in reply to your questions:

  1. Are the chainrings on the 28T replaceable? (which BCD?)

we can offer you a version with 28T chainring OR 130mm BCD adapter, but you need to make a decision in advance; however, if you purchase the 28T version, we can offer you a 37T chainring to be installed on top - please, see this manual: http://efneo.com/filesss/manuals/external-chainring-attachment.pdf
In terms of durability, our 28T chainring is made from chromoly steel 30 HRC, which is much above the standard derailleur chainring, so it simply will never wear in practice (we have clients who covered 15 000 miles, and topic of chainring wearing out did not come up)

  1. What is the weight of the efneo crankset? (please specify if this weight include BottomBracket)

the gearbox weighs 1200g (without bottom bracket, left crank and shifter)

QUESTION: Hello again, Can one of your cranksets be used with Alfine 11?
With a Gates belt?
With a T47 BB?
Can it be used with Di2 shifters?
Stan, Yours.

ANSWER: Dear Stan, my answers below:
Can one of your cranksets be used with Alfine 11? -> Yes
With a Gates belt? -> Yes
With a T47 BB? -> Yes, but you need to use this adapter:
https://candncycles.co.uk/product/8498068/fsa-t47-to-bsa-68-73-83mm-bottom-bracket-adapter-el316/option/
Can it be used with Di2 shifters? -> Yes

QUESTION: I am trying to install one of your systems to a Strida. The drive side crank doesn't seem
to be going on far enough. The official instructions say that I need 30.5mm of axle but mine is measuring 28mm.
Where should I go from here? Taylor.

ANSWER: Dear Taylor,
28mm is ok, please, see the drawing:
http://efneo.com/filesss/manuals/BB-68mm-dim.png
(30.5mm is when you measure together with the BB cup flange)
If you have any other questions, let me know!

Second, please answer the question below by thinking step-by-step.
You can ask for appropriate QUESTION-ANSWER examples as your context, if you consider them helpful.

Context QUESTION-ANSWER examples: {"question": "Hello! I'm hoping you might be able to assist me with a few questions I have about your GTRO in relation with my trike. I have a 2016 AZUB TRIcon 20" trike. I currently have a SRAM DD3 IGH, paired with a nine cog Shimano HG cassette and a single 45T Shimano Alfine 150mm crank. I'm finding myself running out of speed in high gear, e.g. I can't seem to get above 16-18mph going flat in my high gear. I'm curious to find out if the 38T version of your GTRO would allow me a higher top-end speed or would I consider purchasing the adapter unit with a 52T cog, for example? Additionally, would you please tell me which bottom bracket size is compatible with my AZUB trike? Finally, I noticed a $100 off coupon flashed on my screen when I visited your site a bit ago today. Would you please share that coupon code as I missed writing it down? Thanks much, in advance, for any insight you can provide! Regards, Kory", "answer": "Dear Kory, please, see my replies to the points you raised: ...38T version or adapter with 52T? >> our 38T version comes with the adapter (130mm-BCD standard), so you can try the 38T first, >> but if you wish to migrate to 52T, you can do it at any time; >> the 38T chainring will give you "gears" equivalent to 38T-54T-68T which bottom bracket size is compatible with my AZUB trike? >> 68mm-wide (by the way, we tested our gearbox with AZUB) $100 off coupon >> sure, here it is: GTRO100"}
{"question": "Hi, I have a Prioirty Continuum Onyx bike which has a NuVinci/Enviolo N330 hub and Gates s100 Beltdrive Crankset with 50T front CDN chainring and 24T CDX rear cog with a CDN belt. Would the GTRO Efneo drive work with my bike? I think it should. I am not concerned about the bottom bracket requirements of 68 mm and English thread but rather about the front cog and how well to install it. The Gates manual doesn’t approve a 28T front cog with a 24T rear cog. So I am not sure how your drive could possibly work in my bike. However, one of the bike owners in your website testimonials also has a NuVinci hub but uses a bike chain instead of Gates belt so I thought perhaps there is hope for me. Anyway, I just wanted to ask your opinion before I placed an order for it with you. I am willing to pay extra for a customized solution from you.", "answer": "Dear Nolin, the photos that you can see at our website show a Gates front beltring with 46 teeth (28 teeth chainring is used for a standard chain, so this is a different world ;) ). We offer a gearbox with a 5-bolt adapter, at 130mm BCD (5 bolts are included into our product). You can use this beltring with our adapter; we do not sell Gates components: https://www.amazon.com/Gates-Carbon-Drive-CenterTrack-Pulley/dp/B00FUS1MTA. You would probably need to purchase a new belt, probably 22 mm shorter, if I count it correctly. If you have any other questions, please, let me know."}
{"question": "Hallo Wiktor, I have a bike with a 73mm bottom bracket. Do you have an Efneo gearbox that will fit this bike? Thanks, Seon Caimbeul", "answer": "Dear Seon, please write "BB73mm" in the comment, when making a purchase; we will need few days more for making the shipment, but 73mm is available."}
{"question": "Compatibility? Terra Trike Rover, I8 (internal 8 gear rear hub Sturmey Archer ), 32 tooth front ring.", "answer": "Dear Macwildstar, 1// in fact, our gearbox offers three 28T-40T-50T chainrings (the 28T is physical and 40T-50T are vertical), so you may probably want to compare your current 32T with our middle virtual chainring of 40T. If you enlarge your rear sprocket by 25%, you will keep the same ratio with our middle chairing (40T) with the rear sprocket, as you currently have; I see at Sturmey Archer website that they offer rear sprockets with 20, 23 or 25 teeth - what do you have atm?.. BUT, you do not necessarily need to match your current frontrear ratio; simply, we encourage you to first try our gearbox with your original rear sprocket and make a decision based on your experience 2// our gearbox is compatible with rear gearboxes, but you should probably check the Sturmey Archer manual, too 3// our gearbox works with the most typical BB shell, having BSA / ISO / English thread, but I see on photos, that https://www.terratrike.com/shop/rover-i8/ almost for sure uses it; anyway, you may confirm it with terratrike.com or with some bike mechanic 4// however, we are waiting for another batch of gearboxes to come, our current stock is empty; we will send you an email, when we open sales again; sorry for the inconvenience -- Regards, Wiktor Migaszewski +48 692 361 761 -- http://www.efneo.com http://www.efneo.com/patents Efneo Sp. z o.o., KRS 0000492928, Kapitał zakładowy 318 920,00 zł niedz., 16 cze 2019 o 21:25 Efneo napisał(a): > Sent from: [email protected] > Message: Compatibility? Terra Trike Rover, I8 (internal 8 gear rear hub Sturmey Archer ), 32 tooth front ring."}
{"question": "Can the efneo be used with a torque sensing bottom bracket? If so, is there one you can recommend for a 73mm bb shell? Thank you!", "answer": "Dear Mathis, I should have a 73mm version of the Sempu T2.3 sensor: http://efneo.com/filesss/manuals/sempu-documentation.pdf Let me check and get back to you."}
{"question": "Dear Wiktor, I have a GTRO gear box on my Terra Trike recumbent trike and have been pleased by it performance although recently it has started giving me a little trouble. In first gear there is a stiffness in the crank on about the third time around and more frequently in second and in third it is stiff most of the time. I also noticed a rubber seal sticking out of the chainring area and it may be loose. Can you give me some advise on how to remedy this problem? Also will a standard shifter cable work on the GTRO? When installing it I took the cable apart for routing and undid the part toward the gear box and could not get it back together very good, I have some loose cable strands. Thank you Steve Sent from my iPad", "answer": "Dear Steve, in reply to your questions: 1) Can you please send me a photo showing this seal? 2) Yes, you can change the shifting cable using a standard derailleur cable and housing (we use Jagwire 4mm housing), accordingly to this manual: http://efneo.com/filesss/manuals/Shifting-cable-exchange---grip-or-trigger.pdf"}
{"question": "Hi, I have a kona unit 2013 without gears and would like to add your gearbox to it. http://www.efneo.com/gearbox/wp-content/uploads/2019/08/kona-bike.jpg", "answer": "Dear Jonas, based on what I see here*:* http://2013.konaworld.com/bike.cfm?content=unit this bike uses a crankset from FSA*:* FSA CK-7152PDHS (170/175mm) or CK-7050PDHS (180mm) I found another crankset from this FSA line, which uses English / BSA / ISO type of Bottom Bracket (BC 1.37" x 24T thread), which means that frame of your bike is compatible with our gearbox. I do not have 100% certainty, but very very very close ;) You may check at some bike workshop, if you want to know for sure - frame needs to have English / BSA / ISO type of Bottom Bracket (BC 1.37" x 24T thread), this standard dominates on the market. Still, we are currently restocking and will reopen sales around the end of September. We will let you know on you email, when gearbox is again available. In the meantime, if you have any questions, please, feel free to contact us."}
{"question": "I received my Efneo gearbox... Thank you very much. This gearbox is for my Terratrike Rover 8 ext recumbent trike. Inside the package there are 3 rings included. In the pdf instructions I do no see any reference to these rings, nor are they included in the video online. Can you please instruct me as to what these flat rings are for? Thank you Jack Seiler", "answer": "Dear Jack, these rings (we call them BB washers) are there just in case, that you need to move gearbox further away from the bicycle frame (to adjust the chainline or avoid conflict with the bike frame, if gearbox is unnecessarily touching it with bolts, or for other reasons); if your installation goes well without using these BB washers, simply please keep them in some safe place in your workshop :) maybe they will be handy few years from now; any other questions, please, just let me know!"}
{"question": "Hello dear Wiktor, I really hope you are all well? Did you have to close your company? Attached an image of the drive installed, the ugly wire will be replaced by an aluminium bracket asap. (Cable shortening seemed to be a bit tricky just at first sight, but no problem in the end.) Please may I ask also; the tube you are using to cover the coupler - is that heat-shrinking tube? Take care of your health, best wishes, Chris", "answer": "*Dear Chris, * thank you for the photo. Yes, this is heat shrinking. We are working almost normally, we will see. Situation is Poland it quite good, government is doing their job. I was not aware you will use this for recumbent - why didn't you decide to relocate the lever arm, like on this movie? https://vimeo.com/219351462 -- Regards, Wiktor Migaszewski *+48 692 361 761 *"}
{"question": "Dear Sirs and Madames, I have a problem with my gearbox, see attached PDF file. The gearbox in the pictures has not yet been cleaned. I have a few questions about spare parts for my efneo gearbox: I need when four planet gears is normal: 4x bearing axles for the planetary gears 4x thrust washers 1x bearing plate see page 4 of the PDF file. I need when five planet gears is normal: 4x bearing axles for the planetary gears 5x thrust washers 1x bearing plate see page 4 of the PDF file 1x planet gear 1x pawl 1x spring What would the parts cost? All texts are translated with Google. Unfortunately, I do not speak the English language. With best regards Jürgen Schwarzer", "answer": "Dear Juergen, we are very sorry for the inconvenience! It would probably be best, if we fix this gearbox, if you only cover the cost of shipments (50 EUR, fast DPD courier, we have a contract with this company); the shape of the hole is normal; we introduced anti-seizure grease for satellite-axles in the meantime, so the seizure problem is solved already; if you decide to send us the gearbox for fixing, we will let you know how to call our DPD courier (we would need your mobile phone number for courier; he will have the label printed already, he will just come and take the box; please, only send us only the right crank with shifter, no Bottom Bracket, no left crank; we only need two working days for fixing). Please, let me know if this would be a good solution for you."}
QUESTION: Hello Wiktor, I wanted to get a price on your 38t Chainring GTRO with an ERider 73mm torque sensing bottom bracket. I will be using it on my ebike converted MTB. Thanks in advance for your time. Best Regards, Toan
A:


assistant (to ragproxyagent):

Dear Toan,
We can definitely provide you with a 38T Chainring GTRO gearbox. As for the ERider 73mm torque sensing bottom bracket compatibility, we have a solution for 73mm shells as well. When making a purchase, please specify "BB73mm" in the comment. As for the prices, you will have to check our website for the current prices as they may vary. Please, let me know if you have any other questions.


Process finished with exit code 0

'''

jfischburg-us added a commit to jfischburg-us/autogen that referenced this pull request Nov 12, 2023
* Improves clarity and fixes punctuation in README and Multi-agent documentation (microsoft#40)

* Improves clarity and fixes punctuation in README and Multi-agent documentation

* fix broken colab link to agentchat_groupchat_research.ipynb (others are fine)

* fix typos, improves readability

* make retry_time configurable, add doc (microsoft#53)

* make retry_time configurable, add doc

* in seconds

* retry_wait_time

* bump version to 0.1.4

* remove .json

* rename

* time

* Update no_update_context, fix upsert docs (microsoft#52)

* Update no_update_context, fix upsert docs

* Recreate only once

* Add comments to get_or_create

---------

Co-authored-by: Chi Wang <[email protected]>

* Update README.md (microsoft#54)

README update for my profile <3

* retrieve_utils.py - Updated.py to have the ability to parse text from PDF Files (microsoft#50)

* UPDATE - Updated retrieve_utils.py to have the ability to parse text from pdf files

* UNDO - change to recursive condition

* UPDATE - updated agentchat_RetrieveChat.ipynb to clarify which file types are accepted to be in the docs path

* ADD - missing import

* UPDATE - setup.py to have PyPDF2 in retrievechat

* RE-ADD - urls

* ADD - tests for retrieve utils, and removed deprecated PyPdf2

* Update agentchat_RetrieveChat.ipynb

* Update retrieve_utils.py

Fix format

* Update retrieve_utils.py

Replace print with logger

* UPDATE - added more specific exception to PDF decryption try/catch

* FIX - typo, return statement at wrong indentation in extract_text_from_pdf

---------

Co-authored-by: Ward <[email protected]>
Co-authored-by: Li Jiang <[email protected]>

* Bump version to 0.1.5 (microsoft#60)

* typing & docstr update (microsoft#59)

* typing & docstr update

* bump version to 0.1.5

* Updated readme.md : seprated AutoGen and EcoOptGen also removed bibtex (microsoft#43)

* Updated README.md added required changes to previous pull 

new changes :
1. A section containing citation to AutoGen and EcoOptiGen
2. Another section contain citation to MathChat
## Citation  
[AutoGen](https://arxiv.org/abs/2308.08155). 
AND  [EcoOptiGen](https://arxiv.org/abs/2303.04673).
``` 
bibtex
@inproceedings{wu2023autogen,
      title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework},
      author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Shaokun Zhang and Erkang Zhu and Beibin Li and Li Jiang and Xiaoyun Zhang and Chi Wang},
      year={2023},
      eprint={2308.08155},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

bibtex
@inproceedings{wang2023EcoOptiGen,
    title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},
    author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},
    year={2023},
    booktitle={AutoML'23},
}
```

 [MathChat](https://arxiv.org/abs/2306.01337). 

```
bibtex
@inproceedings{wu2023empirical,
    title={An Empirical Study on Challenging Math Problem Solving with GPT-4},
    author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},
    year={2023},
    booktitle={ArXiv preprint arXiv:2306.01337},
}
```

* Seperated AutoGen and EcoOptGen and removed 'bibtex'

## Citation  
[AutoGen](https://arxiv.org/abs/2308.08155). 
``` 
@inproceedings{wu2023autogen,
      title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework},
      author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Shaokun Zhang and Erkang Zhu and Beibin Li and Li Jiang and Xiaoyun Zhang and Chi Wang},
      year={2023},
      eprint={2308.08155},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}
```

[EcoOptiGen](https://arxiv.org/abs/2303.04673).
```
@inproceedings{wang2023EcoOptiGen,
    title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},
    author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},
    year={2023},
    booktitle={AutoML'23},
}
```

* expand faq (microsoft#66)

* expand faq

* models

* fix format error

* minor fix (microsoft#31)

* minor fix for stablility

* fix format

* fix format

* update run_code logic

* format

* Update conversable_agent.py

* fix format

* Update conversable_agent.py

* add tests

* fix format

* revert changes

* Fixed MD Issue (microsoft#72)

* fix append_oai_message (microsoft#47)

* fix append_oai_message

* add testcase for groupchat

* add test_oai to openai workflow

* code formate

* update

* formate

* update

* enable openai workflow on fork branch (microsoft#82)

* update

* update

* Update openai.yml

* bump version to 0.1.6 (microsoft#85)

* spelling error (microsoft#84)

* Format issue (microsoft#69)

* Fixed formating issue in the README

* Fixed the formating issue in the README

* Updated formatting as per review comments

* Refactor README.md to highlight use cases and features

* Updated README as per feedback

* Updated README as per feedback

---------

Co-authored-by: Al-Iqram Elahee <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>

* Replace the use of `assert` in non-test code (microsoft#80)

* Replace `assert`s in the `conversable_agent` module with `if-log-raise`.

* Use a `logger` object in the `code_utils` module.

* Replace use of `assert` with `if-log-raise` in the `code_utils` module.

* Replace use of `assert` in the `math_utils` module with `if-not-raise`.

* Replace `assert` with `if` in the `oai.completion` module.

* Replace `assert` in the `retrieve_utils` module with an if statement.

* Add missing `not`.

* Blacken `completion.py`.

* Test `generate_reply` and `a_generate_reply` raise an assertion error
when there are neither `messages` nor a `sender`.

* Test `execute_code` raises an `AssertionError` when neither code nor
filename is provided.

* Test `split_text_to_chunks` raises when passed an invalid chunk mode.

* * Add `tiktoken` and `chromadb` to test dependencies as they're used in
the `test_retrieve_utils` module.

* Sort the test requirements alphabetically.

* Bump postcss from 8.4.18 to 8.4.31 in /website (microsoft#93)

Bumps [postcss](https://github.com/postcss/postcss) from 8.4.18 to 8.4.31.
- [Release notes](https://github.com/postcss/postcss/releases)
- [Changelog](https://github.com/postcss/postcss/blob/main/CHANGELOG.md)
- [Commits](postcss/postcss@8.4.18...8.4.31)

---
updated-dependencies:
- dependency-name: postcss
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* show github stars (microsoft#92)

* Docs: fixed typos and grammar (microsoft#94)

* openai_utils.py - functionality for instantiating config_list with a .env file (microsoft#68)

* FORMATTING

* UPDATE - OAI __init__.py

* ruff

* ADD - notebook covering oai API configuration options and their different purposes

* ADD openai util updates so that the function just assumes the same environment variable name for all models, also added functionality for adding API configurations like api_base etc.

* ADD - updates to config_list_from_dotenv and tests for openai_util testing, update example notebook

* UPDATE - added working config_list_from_dotenv() with passing tests, and updated notebook

* UPDATE - code and tests to potentially get around the window build permission error, used different method of producing temporary files

---------

Co-authored-by: Ward <[email protected]>

* document about docker (microsoft#119)

* document about docker

* clarify

* dev container

* docs: typo fixed (microsoft#129)

* Fix broken link in README.md (microsoft#134)

The link to the documentation's FAQ#code-execution was broken because the 'docs' directory was missing in the original URL.

Co-authored-by: Qingyun Wu <[email protected]>

* fix doc typo (microsoft#123)

Co-authored-by: Qingyun Wu <[email protected]>

* typo fixed (microsoft#127)

Co-authored-by: Sagar Desai <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>

* bump version to 0.1.7 (microsoft#141)

* Title: Adjust shell language switch in execute_code for Docker usage (microsoft#139)

Description:
This commit modifies the conditional check in execute_code to ensure the switch to PowerShell on Windows only occurs when Docker is not being used. This keeps shell script execution consistent within a Docker container across all platforms, aligning with the function's intended behavior.

Co-authored-by: Xiaoyun Zhang <[email protected]>

* move citation before contributing (microsoft#154)

* bump version to 0.1.8

* add twitter account to website (microsoft#150)

Co-authored-by: Chi Wang <[email protected]>

* Update num tokens from text (microsoft#149)

* Improve num_tokens_from_text

* Format

* Update comments

* Improve docstrings

* add twitter account to start page (microsoft#159)

* Update termination logic (microsoft#155)

* Added twitter link to the contributing section (microsoft#162)

Co-authored-by: vidhula17 <[email protected]>

* fix: replace gpt-35-turbo in model name to gpt-3.5-turbo so the name … (microsoft#138)

* fix: replace gpt-35-turbo in model name to gpt-3.5-turbo so the name string is in the current chat_model list

* ref: reformatted with black

---------

Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>

* Output a warning if attempting to load the OAI_CONFIG_LIST from a file, but the file is not found. (microsoft#174)

* Warn if GroupChat is underpopulatd. (microsoft#170)

* Display a warning if use_docker evlauates to True but the python docker package is not available. (microsoft#172)

Co-authored-by: Qingyun Wu <[email protected]>

* bump version to 0.1.9 (microsoft#177)

Co-authored-by: Qingyun Wu <[email protected]>

* Warn if oai.Completion is provided with an empty config_list (microsoft#178)

Co-authored-by: Qingyun Wu <[email protected]>

* Bump version to 0.1.10 (microsoft#181)

* Add support to customized vectordb and embedding functions (microsoft#161)

* Add custom embedding function

* Add support to custom vector db

* Improve docstring

* Improve docstring

* Improve docstring

* Add support to customized is_termination_msg fucntion

* Add a test for customize vector db with lancedb

* Fix tests

* Add test for embedding_function

* Update docstring

* Fix typo in agentchat_MathChat.ipynb (microsoft#191)

requries -> requires

* Make getting started a little easier (microsoft#180)

* Update README.md

add codespace quick start

* add codespace

* update path

---------

Co-authored-by: Li Jiang <[email protected]>

* Fix edge cases extracting code when the message's content is None (microsoft#205)

* Add md for faqs (microsoft#194)

* Add md for faq; Update readme

* Update TRANSPARENCY_FAQS.md

Co-authored-by: Chi Wang <[email protected]>

* Update TRANSPARENCY_FAQS.md

Co-authored-by: Chi Wang <[email protected]>

* Remove trailing space

* Fix trailing space issue

---------

Co-authored-by: Chi Wang <[email protected]>

* Fix typo in README.md (microsoft#193)

* Icons not centered in the "autogen_agentchat.png" (microsoft#169)

* Delete website/static/img/autogen_agentchat.png

* Add files via upload

* Addresses issue microsoft#199 (microsoft#200)

* Addresses issue microsoft#199

* Fixed comment to align with new behavior.

---------

Co-authored-by: Qingyun Wu <[email protected]>

* Improving logging in oai.completion to show token_count (microsoft#179)

* update

* update doc

---------

Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>

* Update Getting-Started.md (microsoft#213)

Fixed minor typo

Co-authored-by: Chi Wang <[email protected]>

* Added comment about config_list in the README example microsoft#216 (microsoft#218)

* Update README.md

* Update README.md

* fix: be compatible with custom model without full response (microsoft#222)

Co-authored-by: Qingyun Wu <[email protected]>

* Update Installation.md-with detailed explanation on add a period or newline microsoft#219  (microsoft#231)

* Update Installation.md

Usage and importance of Docker is explained in more precise and to the point

* Update website/docs/Installation.md

---------

Co-authored-by: Qingyun Wu <[email protected]>

* Spelling fixes. (microsoft#220)

Co-authored-by: Qingyun Wu <[email protected]>

* Typo (microsoft#234)

* fix typo

* wording

* typo

* bump version to 0.1.11 (microsoft#242)

* bump version to 0.1.11

* fix format issue

* docstr updated for `use_docker` in `execute_code ` (microsoft#233)

* docstr updated

* fixed line 245

* Fixed line 246

* space_traling error Fix_01

* Revert space in '-'

* Fixed line 245 FIX_02

---------

Co-authored-by: Qingyun Wu <[email protected]>

* document retrieve chat (microsoft#258)

* document retrieve chat

* Ran pre commit hook

* Added figure to notebook (microsoft#246)

Co-authored-by: Li Jiang <[email protected]>

* Lancgain tool bridge (microsoft#262) (microsoft#263)

* Added a LangChain tooling bridge example

* Updated Doco

* Update agentchat_langchain.ipynb

remove key

---------

Co-authored-by: Elliot Wood <[email protected]>
Co-authored-by: Li Jiang <[email protected]>

* Add support to custom text spliter (microsoft#270)

* Add support to custom text spliter function and a list of files or urls

* Add parameter to retrieve_config, add tests

* Fix tests

* Fix tests

* Update FAQ.md, elaborate on how to customise docker image and pick 'python:3' to solve typical errors (microsoft#269)

* Update FAQ.md

* Update website/docs/FAQ.md

Co-authored-by: Qingyun Wu <[email protected]>

* Update website/docs/FAQ.md

Co-authored-by: Qingyun Wu <[email protected]>

* Update website/docs/FAQ.md

Co-authored-by: Qingyun Wu <[email protected]>

---------

Co-authored-by: Qingyun Wu <[email protected]>

* Add group chat and retrieve agent example (microsoft#227)

* Add group chat and retrieve agent example

* Fix link and models

* Support call rag in a group chat and not init with rag

* Fix n_results logic

* Update notebook

* Fix format

* Improve wording

* Update variable name

* Revert to main

* Update function call

* Update keys

* Update contents

* Update contents

* docs: added virtual environment setup process (microsoft#249)

* docs: added virtual environment setup process

* Update website/docs/Installation.md

---------

Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Chi Wang <[email protected]>

* Update Getting-Started.md (microsoft#275)

Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>

* Bump @babel/traverse from 7.20.1 to 7.23.2 in /website (microsoft#283)

Bumps [@babel/traverse](https://github.com/babel/babel/tree/HEAD/packages/babel-traverse) from 7.20.1 to 7.23.2.
- [Release notes](https://github.com/babel/babel/releases)
- [Changelog](https://github.com/babel/babel/blob/main/CHANGELOG.md)
- [Commits](https://github.com/babel/babel/commits/v7.23.2/packages/babel-traverse)

---
updated-dependencies:
- dependency-name: "@babel/traverse"
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Add a blog for RAG agents (microsoft#284)

* Init blog

* Update blog

* Add more contents

* Restore notebook

* function call filter in group chat (microsoft#294)

* function call filter in group chat

* find agents with function_map

* fix typo in website/blog/2023-05-18-GPT-adaptive-humaneval/index.mdx (microsoft#299)

Co-authored-by: Qingyun Wu <[email protected]>

* Organize notebooks into logical groups microsoft#273 (microsoft#288)

* Organize notebooks into logical groups microsoft#273

* update multiagent group to mention >3 agents

* Update docs (microsoft#297)

Co-authored-by: Qingyun Wu <[email protected]>

* Update README.md with Roadmap. (microsoft#304)

also removed ugly periods. fixes: microsoft#289 (comment)

Co-authored-by: Qingyun Wu <[email protected]>

* bump version to 0.1.12 (microsoft#301)

Co-authored-by: Qingyun Wu <[email protected]>

* doc: Update FAQ.md (microsoft#282)

Isssue microsoft#277

* Fix format and links in documentations (microsoft#310)

* Fix format and links

* Update title

* Sync title

* Add examples to installation

* update oai models (microsoft#316)

* guidance for contribution (microsoft#320)

* TeachableAgent (microsoft#278)

* Initial commit.

* Disable LLM response caching.

* Add teachability option to setup.py

* Modify test to use OAI_CONFIG_LIST as suggested in the docs.

* Expand unit test.

* Complete unit test.

* Add filter_dict

* details

* AnalysisAgent

* details

* More documentation and debug output.

* Support retrieval of any number of relevant memos, including zero.

* More robust analysis separator.

* cleanup

* teach_config

* refactoring

* For robustness, allow more flexibility on memo storage and retrieval.

* de-dupe the retrieved memos.

* Simplify AnalysisAgent. The unit tests now pass with gpt-3.5

* comments

* Add a verbosity level to control analyzer messages.

* refactoring

* comments

* Persist memory on disk.

* cleanup

* Use markdown to format retrieved memos.

* Use markdown in TextAnalyzerAgent

* Add another verbosity level.

* clean up logging

* notebook

* minor edits

* cleanup

* linter fixes

* Skip tests that fail to import openai

* Address reviewer feedback.

* lint

* refactoring

* Improve wording

* Improve code coverage.

* lint

* Use llm_config to control caching.

* lowercase notebook name

* Sort out the parameters passed through to ConversableAgent, and supply full docstrings for the others.

* lint

* Allow TextAnalyzerAgent to be given a different llm_config than TeachableAgent.

* documentation

* Modifications to run openai workflow.

* Test on just python 3.10.
Replace agent with agent teachable_agent as recommended.

* Test on python 3.9 instead of 3.10.

* Remove space from name -> teachableagent

---------

Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Chi Wang <[email protected]>

* bump version to 0.1.13 (microsoft#333)

* add downloads stats in readme (microsoft#334)

* Added Roadmap to Getting-Started.md (microsoft#324)

* Resolves Typo Correction microsoft#336 (microsoft#338)

Co-authored-by: Chi Wang <[email protected]>

* Update README.md (microsoft#321)

Co-authored-by: Qingyun Wu <[email protected]>

* Updating Examples to follow new categorical structure. microsoft#273 (microsoft#327)

* Updating Examples to follow new categorical structure. microsoft#273

Addressing the remaining task for microsoft#273, I have copied over the changes from /Usecases to /Examples to follow the new categorical example notebooks structure.

* Add the new example notebook

---------

Co-authored-by: Qingyun Wu <[email protected]>

* Update agentchat_auto_feedback_from_code_execution.ipynb (microsoft#342)

Co-authored-by: Chi Wang <[email protected]>

* Update agentchat_MathChat.ipynb (microsoft#341)

* Fix grammar and spelling in agentchat_chess.ipynb (microsoft#346)

* Improve readability for agentchat_function_call.ipynb (microsoft#347)

* Improve readability in agentchat_groupchat_research.ipynb (microsoft#350)

* Improve readability in agentchat_groupchat_research.ipynb

* Undo updates to system message.

* format (microsoft#358)

* Improve readability in oai_openai_utils.ipynb (microsoft#365)

* Improve readability in oai_completion.ipynb (microsoft#364)

Co-authored-by: Chi Wang <[email protected]>

* Fix grammar for agentchat_web_info.ipynb (microsoft#362)

Co-authored-by: Chi Wang <[email protected]>

* Improve readability for agentchat_two_users.ipynb (microsoft#361)

Co-authored-by: Chi Wang <[email protected]>

* Fix grammar in agentchat_stream.ipynb (microsoft#357)

Co-authored-by: Chi Wang <[email protected]>

* Fix grammar and spelling in agentchat_planning.ipynb (microsoft#356)

Co-authored-by: Chi Wang <[email protected]>

* Fix the grammar and spelling in agentchat_human_feedback.ipynb (microsoft#354)

Co-authored-by: Chi Wang <[email protected]>

* Update agentchat_langchain.ipynb (microsoft#355)

Co-authored-by: Chi Wang <[email protected]>

* headsup about dependency change (microsoft#378)

* headsup about dependency change

* more change

* Add link to OptiGuide microsoft#371 (microsoft#376)

* OptiGuide Link

* Update AutoGen-AgentChat.md

* fixes

* Update docs in RetrieveChat notebook and Installation (microsoft#379)

* Update comments to make it more clear

* Update Installation

* config list for test (microsoft#395)

* Supporting MultiModal Models: an example with LLaVA Notebook (microsoft#286)

* LMM notebook

* Use "register_reply" instead.

* Loop check LLaVA non-empty response

* Run notebook

* Make the llava_call function more flexible

* Include API for LLaVA from Replicate

* LLaVA data format update x2
1. prompt formater function
2. conversation format with SEP

* Coding example added

* Rename "ImageAgent" -> "LLaVAAgent"

* Docstring and comments updates

* Debug notebook: Remote LLaVA tested

* Example 1: remove system message

* MultimodalConversableAgent added

* Add gpt4v_formatter

* LLaVA: update example 1

* LLaVA: Add link to "Table of Content"

* using thread safe timeout to allow code execution to be compatible with multi-threading/multi-processing (microsoft#224)

Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Victor Dibia <[email protected]>
Co-authored-by: Chi Wang <[email protected]>

* Fix tmp dir not exists (microsoft#401)

* Fix tmp dir not exists

* Update tests to make it more clear

* Add check if save path is not None

* feat: Qdrant vector store support (microsoft#303)

* feat: QdrantRetrieveUserProxyAgent

* fix: QdrantRetrieveUserProxyAgent docstring

* chore: batch of 500 all CPU cores

* chore: conditional import for tests

* chore: config parallel, batch 100

* chore: collection creation params

* chore: conditonal payload indexing
fastembed import check

* docs: notebook for QdrantRetrieveUserProxyAgent

* docs: update docs link

* docs: notebook examples update

* chore: hnsw, payload index reference

* docs: notebook docs_path update

* Update test/agentchat/test_qdrant_retrievechat.py

Co-authored-by: Li Jiang <[email protected]>

* chore: update notebook output

* Fix format

---------

Co-authored-by: Li Jiang <[email protected]>

* [Blocking Issue] Add tests dependencies for qdrant and fix chromadb errors (microsoft#435)

* Add tests dependencies for qdrant

* Update chromadb API

* Update chromadb API version

* Fix typehint

* Add py 3.9 condition

* Fix client creation error

* TeachableAgent blog post (microsoft#436)

* Authors

* initial checkin

* completed blog post

* trim trailing whitespace

* date

* Address reviewer feedback.

* Adds jupyter as a vscode extension, fix validation errors in devcontainer.json (microsoft#433)

* Adds jupyter as a vscode extension, fix validation errors in vscode (see https://containers.dev/supporting#visual-studio-code)

* Trim trailing whitespace

* Add newline to end of file

---------

Co-authored-by: Li Jiang <[email protected]>

* Update FAQ section in documentation (microsoft#390)

* UPDATE - FAQ section in documentation

* FIX - formatting test failure

* FIX - added disclaimer

* pre-commit

* Update website/docs/FAQ.md

Co-authored-by: Chi Wang <[email protected]>

* Update website/docs/FAQ.md

Co-authored-by: Chi Wang <[email protected]>

* Update website/docs/FAQ.md

Co-authored-by: Chi Wang <[email protected]>

* UPDATE - notebook and FAQ information for config_list_from_models

---------

Co-authored-by: Ward <[email protected]>
Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: Li Jiang <[email protected]>

* Add token_count_util (microsoft#421)

* add token_count_util

* remove token_count from retrieval util

* format

* update dependency

* update test

* spelling fix for Update math_user_proxy_agent.py (microsoft#431)

Co-authored-by: Chi Wang <[email protected]>

* bump version to 0.1.14 (microsoft#400)

* bump version to 0.1.14

* endpoint

* test

* test

* add ipython to retrievechat dependency

* constraints

* target

* Update Installation.md (microsoft#456)

* Update Installation.md

Replace autogen->pyautogen in env setup to avoid confusion

Related issue: microsoft#211

* Update Installation.md

Add deactivation instructions

* Update website/docs/Installation.md

Co-authored-by: Chi Wang <[email protected]>

---------

Co-authored-by: Chi Wang <[email protected]>

* Update FAQ with workaround for Issue microsoft#251 (microsoft#405)

* Update FAQ with workaround for Issue microsoft#251

* Update website/docs/FAQ.md

* Update website/docs/FAQ.md

---------

Co-authored-by: Chi Wang <[email protected]>

* Fix typo in README.md (microsoft#481)

Contributers -> Contributors

* Fix/async function and tool execution (microsoft#87)

* async run group chat

* conversible agent allow async functions to generate reply

* test for async execution

---------

Co-authored-by: Qingyun Wu <[email protected]>
Co-authored-by: Chi Wang <[email protected]>

* Adding async support to get_human_input (microsoft#466)

* Adding async support to get_human_input

* Adjust code for Code formatting testing fail

* Adjust the test_async_get_human_input.py to run async on test

* Adjust the test_async_get_human_input.py for pre-commit-check error

* Adjust the test_async_get_human_input.py for pre-commit-check error v2

* Adjust remove unnecessary register_reply

* Adjust test to use asyncio call

* Adjust go back to not use asyncio

* Added example .txt file for agentchat_langchain sample notebook (microsoft#373)

* Added example .txt file for agentchat_langchain sample notebook

* Update radius.txt

---------

Co-authored-by: Chi Wang <[email protected]>

* Update README.md (microsoft#506)

Co-authored-by: Chi Wang <[email protected]>

* Dev/v0.2 (microsoft#393)

* api_base -> base_url (microsoft#383)

* InvalidRequestError -> BadRequestError (microsoft#389)

* remove api_key_path; close microsoft#388

* close microsoft#402 (microsoft#403)

* openai client (microsoft#419)

* openai client

* client test

* _client -> client

* _client -> client

* extra kwargs

* Completion -> client (microsoft#426)

* Completion -> client

* Completion -> client

* Completion -> client

* Completion -> client

* support aoai

* fix test error

* remove commented code

* support aoai

* annotations

* import

* reduce test

* skip test

* skip test

* skip test

* debug test

* rename test

* update workflow

* update workflow

* env

* py version

* doc improvement

* docstr update

* openai<1

* add tiktoken to dependency

* filter_func

* async test

* dependency

* migration guide (microsoft#477)

* migration guide

* change in kwargs

* simplify header

* update optigude description

* deal with azure gpt-3.5

* add back test_eval_math_responses

* timeout

* Add back tests for RetrieveChat (microsoft#480)

* Add back tests for RetrieveChat

* Fix format

* Update dependencies order

* Fix path

* Fix path

* Fix path

* Fix tests

* Add not run openai on MacOS or Win

* Update skip openai tests

* Remove unnecessary dependencies, improve format

* Add py3.8 for testing qdrant

* Fix multiline error of windows

* Add openai tests

* Add dependency mathchat, remove unused envs

* retrieve chat is tested

* bump version to 0.2.0b1

---------

Co-authored-by: Li Jiang <[email protected]>

* Added a simple Testbed tool for repeatedly running templated Autogen scenarios with tightly-controlled initial conditions. (microsoft#455)

* Initial commit of the autogen testbed environment.

* Fixed some typos in the Testbed README.md

* Added some stricter termination logic to the two_agent scenario, and swiched the logo task from finding Autogen's logo, to finding Microsoft's (it's easier)

* Added documentation to testbed code in preparation for PR

* Added a variation of HumanEval to the Testbed. It is also a reasonable example of how to integrate other benchmarks.

* Removed ChatCompletion.start_logging and related features. Added an explicit TERMINATE output to HumanEval to save 1 turn in each conversation.

* Added metrics utils script for HumanEval

* Updated the requirements in the README.

* Added documentation for HumanEval csv schemas

* Standardized on how the OAI_CONFIG_LIST is handled.

* Removed dot-slash from 'includes' path for cross-platform compatibility

* Missed a file.

* Updated readme to include known-working versions.

* Fix typo import autogen (microsoft#549)

* Add support to unstructrued (microsoft#501)

* Add support to unstructrued

* Fix tests

* Add test and documents

* Fix tests

* Fix tests

* Test unstructured on linux and mac

* Update TRANSPARENCY_FAQS.md (microsoft#492)

fixed grammatical error
FAQ--->FAQs

Co-authored-by: gagb <[email protected]>

* Update README.md (microsoft#507)

Fixed small typos

Co-authored-by: Chi Wang <[email protected]>

* fix wrong 'Langchain Provided Tools as Functions' doc ref (microsoft#495)

Co-authored-by: Chi Wang <[email protected]>

* copy dicts before modifying (microsoft#551)

* copy dicts before modifying

* update notebooks

* update notebooks

* close microsoft#567

* Large Multimodal Models in AgentChat (microsoft#554)

* LMM Code added

* LLaVA notebook update

* Test cases and Notebook modified for OpenAI v1

* Move LMM into contrib
To resolve test issues and deploy issues
In the future, we can install pillow by default, and then move back
LMM agents into agentchat

* LMM test setup update

* try...except... clause for LMM tests

* disable patch for llava agent test
To resolve dependencies issue for build

* Add LMM Blog

* Change docstring for LMM agents

* Docstring update patch

* llava: insert reply at position 1 now
So, it can still handle human_input_mode
and max_consecutive_reply

* Resolve comments
Fixing: typos, blogs, yml, and add OpenAIWrapper

* Signature typo fix for LMM agent: system_message

* Update LMM "content" from latest OpenAI release
Reference  https://platform.openai.com/docs/guides/vision

* update LMM test according to latest OpenAI release

* Fully support GPT-4V now
1. Add a notebook for GPT-4V. LLava notebook also updated.
2. img_utils updated
3. GPT-4V formatter now return base64 image with mime type
4. Infer mime type directly from b64 image content (while loading
   without suffix)
5. Test cases modified according to all the related changes.

* GPT-4V link updated in blog

---------

Co-authored-by: Chi Wang <[email protected]>

* update version of openai dependency (microsoft#588)

* Notebook/hierarchy flow (microsoft#482)

* Notebook showing how to use select speaker to control conversation flow.

* pytest associated with notebook.

* Added llm_config to assistant and user proxy agent, and clarified why we set use_cache to false, as requested in the review.

* Added a @pytest.mark.skipif decorator like other tests to run it only in one py version, 3.10

* Fixed config warning.

* Removd llm_config to UserProxyAgent

* Fixed minor typos.

* Reran outputs

* Remopved llm_config from user_proxy_agent

* Colab Badge link updated.

* pre-commit formatting changes.

* Fixed base_url

---------

Co-authored-by: Chi Wang <[email protected]>

* seed -> cache_seed (microsoft#600)

* Added link to the new notebook (microsoft#594)

* update return type of WolframAlphaAPIWrapper.run() (microsoft#523)

* update return type of WolframAlphaAPIWrapper.run

* replace tuple by typing.Tuple

---------

Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: Yiran Wu <[email protected]>

* news update (microsoft#609)

* news update

* separate lines

* Add EcoAssistant to the research page (microsoft#612)

* Update Research.md

* Update Research.md

* Update Research.md

* Add CompressibleAgent (microsoft#443)

* api_base -> base_url (microsoft#383)

* InvalidRequestError -> BadRequestError (microsoft#389)

* remove api_key_path; close microsoft#388

* close microsoft#402 (microsoft#403)

* openai client (microsoft#419)

* openai client

* client test

* _client -> client

* _client -> client

* extra kwargs

* Completion -> client (microsoft#426)

* Completion -> client

* Completion -> client

* Completion -> client

* Completion -> client

* support aoai

* fix test error

* remove commented code

* support aoai

* annotations

* import

* reduce test

* skip test

* skip test

* skip test

* debug test

* rename test

* update workflow

* update workflow

* env

* py version

* doc improvement

* docstr update

* openai<1

* add compressibleagent

* revise doc, add tests, add example

* fix link

* fix link

* fix link

* remove test

* update doc

* update doc

* add tiktoken to dependency

* filter_func

* async test

* dependency

* revision

* migration guide (microsoft#477)

* migration guide

* change in kwargs

* simplify header

* update optigude description

* update for dev

* revision

* revision

* allow not compressing last n msgs

* update

* correct merge

* update test workflow

* check test

* update for test

* update

* update notebook

* update

* fix bug

* update

* update

* update

* check to "pull_request_target" in contrib-openai

---------

Co-authored-by: Chi Wang <[email protected]>

* add AutoGen paper info at the beginning of readme (microsoft#621)

* add paper info on top of readme

* update info

* add paper info

* revise date

* Update oai_completion.ipynb (microsoft#623)

Missing import

* Added warnings for some GroupChat misconfigurations and selection errors (microsoft#603)

* Added warnings for some GroupChat misconfigurations and selection errors

* Fixed formatting

* Introducing Experimental GPT Assistant Agent  in AutoGen (microsoft#616)

* add gpt assistant agent

* complete code

* Inherit class ConversableAgent

* format code

* add code comments

* add test case

* format code

* fix test

* format code

* Improve GPTAssistant

* Use OpenAIWrapper to create client
* Implement clear_history()
* Reply message formatting improvements
* Handle the case when content contains image files

* README update

* Fix doc string of methods

* add multiple conversations support

* Add GPT Assistant Agent into README

* fix test

---------

Co-authored-by: gagb <[email protected]>
Co-authored-by: Beibin Li <[email protected]>

* added twitter(X) banner + link to readme (microsoft#615)

* added twitter(X) banner + link to readme

* Update README.md

Fix typo in the label

---------

Co-authored-by: gagb <[email protected]>

* Enable streaming support for openai v1 (microsoft#597)

* Enable streaming support for openai v1

* Added tests for openai client streaming

* Fix test_completion_stream

* improve readme (microsoft#630)

* improve readme

* Update README.md

Co-authored-by: Chi Wang <[email protected]>

---------

Co-authored-by: Chi Wang <[email protected]>

* Handled possible unclear IndexError in ConversableAgent.last_message method (microsoft#622)

* Handled possible IndexError in ConversableAgent.last_message method with more clear error message and added test in test_conversable_agent.py.

* Fix code formatting issues.

---------

Co-authored-by: Chi Wang <[email protected]>

* Fix test error of compressible agent (microsoft#631)

* fix bug in test

* update workflow

* update

* deepcopy to copy

* Fix docstring of get_or_create (microsoft#583)

* Fix docstring of get_or_create

* Improve docstring

* Refactor GPTAssistantAgent  (microsoft#632)

* Refactor GPTAssistantAgent constructor to handle
instructions and overwrite_instructions flag

- Ensure that `system_message` is always consistent with `instructions`
- Ensure provided instructions are always used
- Add option to permanently modify the instructions of the assistant

* Improve default behavior

* Add a test; add method to delete assistant

* Add a new test for overwriting instructions

* Add test case for when no instructions are given for existing assistant

* Add pytest markers to test_gpt_assistant.py

* add test in workflow

* update

* fix test_client_stream

* comment out test_hierarchy_

---------

Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: kevin666aa <[email protected]>

* uncomment test (microsoft#640)

---------

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: Juanma Cuevas <[email protected]>
Co-authored-by: Chi Wang <[email protected]>
Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Ali Eren SALKIM <[email protected]>
Co-authored-by: Aaron <[email protected]>
Co-authored-by: Ward <[email protected]>
Co-authored-by: Priyanshu Yashwant Deshmukh <[email protected]>
Co-authored-by: Xiaoyun Zhang <[email protected]>
Co-authored-by: Hiftie <[email protected]>
Co-authored-by: Yiran Wu <[email protected]>
Co-authored-by: Shaurya Rohatgi <[email protected]>
Co-authored-by: Al-Ekram Elahee Hridoy <[email protected]>
Co-authored-by: Al-Iqram Elahee <[email protected]>
Co-authored-by: Qingyun Wu <[email protected]>
Co-authored-by: Mohamed Attia <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Ujjwal gupta <[email protected]>
Co-authored-by: lars.gersmann <[email protected]>
Co-authored-by: Hyung-Taik Choi <[email protected]>
Co-authored-by: Tristan Murphy <[email protected]>
Co-authored-by: Sagar Desai <[email protected]>
Co-authored-by: Sagar Desai <[email protected]>
Co-authored-by: mrauter1 <[email protected]>
Co-authored-by: Manish Kumar <[email protected]>
Co-authored-by: Olaoluwa Ademola Salami <[email protected]>
Co-authored-by: Olaoluwa Ademola Salami <[email protected]>
Co-authored-by: Vidhula <[email protected]>
Co-authored-by: vidhula17 <[email protected]>
Co-authored-by: Allen Shi <[email protected]>
Co-authored-by: afourney <[email protected]>
Co-authored-by: afourney <[email protected]>
Co-authored-by: Li Jiang <[email protected]>
Co-authored-by: Ikko Eltociear Ashimine <[email protected]>
Co-authored-by: wayliums <[email protected]>
Co-authored-by: Manuel Saelices <[email protected]>
Co-authored-by: gagb <[email protected]>
Co-authored-by: Deepanshu <[email protected]>
Co-authored-by: Gaëtan H <[email protected]>
Co-authored-by: Javid Jamae <[email protected]>
Co-authored-by: Sheetali Maity <[email protected]>
Co-authored-by: James Tsang <[email protected]>
Co-authored-by: Hitesh Bansal <[email protected]>
Co-authored-by: Shruti Patel <[email protected]>
Co-authored-by: Gourav <[email protected]>
Co-authored-by: Elliot Wood <[email protected]>
Co-authored-by: Maxim Saplin <[email protected]>
Co-authored-by: Ayush Kumar Pandit <[email protected]>
Co-authored-by: Surav Shrestha <[email protected]>
Co-authored-by: Victor Dibia <[email protected]>
Co-authored-by: Haseeb Ansari <[email protected]>
Co-authored-by: Ricky Loynd <[email protected]>
Co-authored-by: Sean Connelly <[email protected]>
Co-authored-by: Ishita Pathak <[email protected]>
Co-authored-by: Ansh Babbar <[email protected]>
Co-authored-by: Beibin Li <[email protected]>
Co-authored-by: Ragy Abraham <[email protected]>
Co-authored-by: Anush <[email protected]>
Co-authored-by: Craig Presti <[email protected]>
Co-authored-by: rajpal <[email protected]>
Co-authored-by: Marc Green <[email protected]>
Co-authored-by: Aayush Chhabra <[email protected]>
Co-authored-by: bonadio <[email protected]>
Co-authored-by: Jason Holtkamp <[email protected]>
Co-authored-by: Aditya <[email protected]>
Co-authored-by: hung_ng__ <[email protected]>
Co-authored-by: gfggithubleet <[email protected]>
Co-authored-by: Vatsalya Vyas <[email protected]>
Co-authored-by: AkariLan <[email protected]>
Co-authored-by: Joshua Kim <[email protected]>
Co-authored-by: 1073710317 <[email protected]>
Co-authored-by: Jieyu Zhang <[email protected]>
Co-authored-by: Andreas Volkmann <[email protected]>
Co-authored-by: Ian <[email protected]>
Co-authored-by: Beibin Li <[email protected]>
Co-authored-by: Malik Muhammad Moaz <[email protected]>
Co-authored-by: Alvaro Mateos <[email protected]>
Co-authored-by: wonderful <[email protected]>
Co-authored-by: kevin666aa <[email protected]>
whiskyboy pushed a commit to whiskyboy/autogen that referenced this pull request Apr 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

RAG-agent max_consecutive_auto_reply doesn't work as expected
4 participants