zylon-ai/private-gpt

Issues

• [BUG] TypeError: llama_index.core.ingestion.pipeline.run_transformations() got multiple values for keyword argument 'show_progress'

  #2133 opened a month ago by yaziciali
  2

• [QUESTION] How to prevent defaulting to gpt2 as tokenizer. reserved_special _token error

  #2135 opened a month ago by Gavin-oleary
  0

• [BUG] BLAS=0 and no GPU usage when built with Llama-cpp with GPU support

  #2107 opened 3 months ago by KianRK
  1

• [BUG] Dependency conflict while using Apple Silicon (Mac M1) Metal GPU.

  #2076 opened 4 months ago by harshadvekariya
  2

• Verify Model Support for Transcription Functionality

  #2134 opened a month ago by akshayjalluri6
  0

• [QUESTION] Correct example for bash to chat with RAG via curl?

  #2121 opened 2 months ago by mmeiste
  2

• [QUESTION] When I ingest a file, the following error was reported. Has anyone encountered a similar problem?

  #2100 opened 3 months ago by cuteyang
  5

• [BUG] Summarize fails even when a model response is generated with the error "HTTP request failed: POST predict: Post "http://127.0.0.1:36333/completion": EOF"

  #2131 opened 2 months ago by SuperSonnix71
  4

• [QUESTION] multi-chat option

  #2126 opened 2 months ago by lopatkovn
  1

• [BUG] Async (nested sync detected) error in UI when summarizing large/long text files

  #2080 opened 4 months ago by Stego72
  5

• [BUG] Unable to process PDF files containing Traditional Chinese characters, reporting encoding errors

  #2129 opened 2 months ago by ulnit
  1

• [QUESTION] - Optimization - 30 millions vectors of 3072 dimensions in 1 collection - How to quickly retrieve top_10k ?

  #2128 opened 2 months ago by nicmax09
  0

• [FEATURE] API endpoint for integration with Microsoft Word

  #2127 opened 2 months ago by GPTLocalhost
  0

• Cannot use of GPU with CUDA instead only CPU which is very slow

  #2083 opened 4 months ago by dadupriv
  3

• [BUG] Potential Performance Degradation with Large Document Sets

  #2122 opened 2 months ago by T-Ezzoury
  0

• [BUG] TypeError: missing a required argument: 'messages'

  #2088 opened 4 months ago by h14turbo
  11

• [QUESTION] Ingesting Excel Files

  #2111 opened 3 months ago by Likhitha075
  3

• [BUG] when accessing landing page prompt is not set/send automatically

  #2119 opened 2 months ago by mmeiste
  0

• [QUESTION] How to run with ollama and mistral-nemo model?

  #2118 opened 2 months ago by exander77
  0

• [QUESTION] How to check embedding progress

  #2117 opened 2 months ago by exander77
  0

• [BUG] Private GPT has infinite loop of responce

  #2112 opened 3 months ago by SpkArtZen
  5

• [BUG] GUI not working

  #2109 opened 3 months ago by ashunaveed
  1

• [BUG] PrivateGPT only uses 2 ingested documents

  #2108 opened 3 months ago by SpkArtZen
  0

• [BUG] PrivateGPT only able to hold 2 files in its context?

  #2102 opened 3 months ago by gupp41
  3

• [BUG] Docker Desktop throwing me a bunch of errors before crashing

  #2106 opened 3 months ago by paulsybrandy
  3

• [QUESTION] cannot change settings when using docker compose

  #2103 opened 3 months ago by Just-enki
  2

• [FEATURE] Allow Open-WebUI as an optional UI

  #2105 opened 3 months ago by kpcrash
  0

• [BUG] Quickstart Ollama External API - GET http://ollama:11434/api/tags "HTTP/1.1 403 Forbidden"

  #2066 opened 5 months ago by reysic
  9

• [QUESTION] Multi-User Environment

  #2101 opened 3 months ago by gulilker
  0

• [BUG] Correct response but hallucinated questions/answers included

  #2099 opened 3 months ago by rmuhawieh
  0

• PrivateGPT UI to Call the Correct Endpoint - Qdrant

  #2098 opened 3 months ago by Aconnia
  0

• [BUG] issue with parsing message history in RAG

  #2093 opened 4 months ago by SilverSeed93
  0

• [BUG] cannot import name 'BaseQueryEngine' from 'llama_index.core'

  #2085 opened 4 months ago by zdavatz
  10

• [QUESTION] Unable to Load Multiple tabs of Locally Running Instance

  #2086 opened 4 months ago by Sanjit0910
  0

• [BUG] Failed to connect to Ollama

  #2071 opened 5 months ago by mwsmws22
  5

• [BUG] Invalid buffer size

  #2082 opened 4 months ago by fred-gb
  0

• [QUESTION] Ingest with space in folder name

  #2081 opened 4 months ago by fred-gb
  0

• Change chunking/splitting method from SentenceWindowNodeParser to JSONNodeParser

  #2072 opened 4 months ago by Beet-Farms
  2

• Ingested Files

  #2074 opened 4 months ago by redkit75
  1

• [QUESTION] How to intergrate Llama_index WorkFlow in private-GPT ?

  #2069 opened 5 months ago by Vela-zz
  1

• [BUG] ERROR: byte not found in vocab:

  #2061 opened 5 months ago by linhcentrio
  0

• [BUG] torch.OutOfMemoryError: CUDA out of memory when ingesting JSON/CSV Files

  #2058 opened 5 months ago by EEmlan
  2

• [BUG] UI keeps track of only the first 20 messages in the chat history

  #2053 opened 5 months ago by rohans30
  1

• [QUESTION] Is there a memory leak in huggingface embedding with pipeline mode

  #2054 opened 5 months ago by mshakirDr
  1

• [QUESTION] Support for Llama on Azure AI Studio

  #2050 opened 5 months ago by aulkiller
  3

• [QUESTION] Semantic Chunking

  #2051 opened 5 months ago by gulilker
  1

• Model won´t query when enabling Rerank in settings-local.yaml[BUG]

  #2032 opened 5 months ago by Castolus
  0

• error in poetry install --extras "llms-llama-cpp vector-stores-qdrant ui embeddings-huggingface"

  #2023 opened 5 months ago by Cassioneto
  2

• Recipes: Summarization

  #2024 opened 5 months ago by jaluma
  0

• [FEATURE] add chat history option

  #2026 opened 5 months ago by socir9
  0